|
|
@@ -40,224 +40,223 @@ Let's read some awesome Automated Machine Learning (AutoML) papers. |
|
|
|
--- |
|
|
|
|
|
|
|
## Neural Architecture Search |
|
|
|
<!-- highly referenced from https://github.com/D-X-Y/Awesome-AutoDL --> |
|
|
|
|
|
|
|
<!-- highly referenced from https://github.com/D-X-Y/Awesome-AutoDL --> |
|
|
|
|
|
|
|
### 2021 |
|
|
|
|
|
|
|
| Title | Venue | Code | Note | |
|
|
|
| :----------------------------------------------------------: | :-----: | :------------------------------------------------: | ------------------------------------------------------------ | |
|
|
|
| [ProxyBO: Accelerating Neural Architecture Search via Bayesian Optimization with Zero-cost Proxies](https://arxiv.org/pdf/2110.10423.pdf) | ArXiv.2021.10 | | [LeiZhang](https://git.openi.org.cn/isleizhang):[NOTE](https://git.openi.org.cn/PCL_AutoML/bbobenchmark/src/commit/55de41b8d14c0fd936629b25785d487dfd8a5f73/docs/NAS_paper_reading/ProxyBO_%20Accelerating%20Neural%20Architecture%20Search%20via%20Bayesian%20Optimization%20with%20Zero-cost%20Proxies.pdf) | |
|
|
|
| [Approximate Neural Architecture Search via Operation Distribution Learning](https://arxiv.org/abs/2111.04670) | ArXiv.2021.08 | | [LeiZhang](https://git.openi.org.cn/isleizhang):[Note](https://git.openi.org.cn/PCL_AutoML/bbobenchmark/src/commit/55de41b8d14c0fd936629b25785d487dfd8a5f73/docs/NAS_paper_reading/Approximate%20Neural%20Architecture%20Search%20via%20Operation%20Distribution%20Learning%20.pdf) | |
|
|
|
| [Searching by Generating: Flexible and Efficient One-Shot NAS with Architecture Generator](https://openaccess.thecvf.com/content/CVPR2021/papers/Huang_Searching_by_Generating_Flexible_and_Efficient_One-Shot_NAS_With_Architecture_CVPR_2021_paper.pdf) | CVPR | [Github](https://github.com/eric8607242/SGNAS) | | |
|
|
|
| [Speedy Performance Estimation for Neural Architecture Search](https://arxiv.org/pdf/2006.04492.pdf) | NeurIPS | [Github](https://github.com/rubinxin/TSE) | [LeiZhang](https://git.openi.org.cn/isleizhang):[NOTE](https://git.openi.org.cn/PCL_AutoML/bbobenchmark/src/commit/55de41b8d14c0fd936629b25785d487dfd8a5f73/docs/NAS_paper_reading/Speedy%20Performance%20Estimation%20for%20Neural%20Architecture%20Search.pdf) | |
|
|
|
| [Generic Neural Architecture Search via Regression](https://proceedings.neurips.cc/paper/2021/file/aba53da2f6340a8b89dc96d09d0d0430-Paper.pdf) | NeurIPS | [Github](https://github.com/leeyeehoo/GenNAS) | [XiangFei](https://git.openi.org.cn/xfey):[NOTE](https://git.openi.org.cn/PCL_AutoML/AutoML/src/commit/62eed82bdd15b338ca09dfea26b5a8a77debd376/docs/notes/nas/Generic%20Neural%20Architecture%20Search%20via%20Regression.pdf) | |
|
|
|
| [Learning Latent Architectural Distribution in Differentiable Neural Architecture Search via Variational Information Maximization](https://openaccess.thecvf.com/content/ICCV2021/html/Wang_Learning_Latent_Architectural_Distribution_in_Differentiable_Neural_Architecture_Search_via_ICCV_2021_paper.html) | ICCV | | [LeiZhang](https://git.openi.org.cn/isleizhang):[NOTE](https://git.openi.org.cn/PCL_AutoML/bbobenchmark/src/commit/55de41b8d14c0fd936629b25785d487dfd8a5f73/docs/NAS_paper_reading/Learning%20Latent%20Architectural%20Distribution%20in%20Differentiable%20Neural%20Architecture%20Search%20via%20Variational%20Information%20Maximization.pdf) | |
|
|
|
| [Not All Operations Contribute Equally: Hierarchical Operation-adaptive Predictor for Neural Architecture Search](https://openaccess.thecvf.com/content/ICCV2021/papers/Chen_Not_All_Operations_Contribute_Equally_Hierarchical_Operation-Adaptive_Predictor_for_Neural_ICCV_2021_paper.pdf) | ICCV | | [XiangFei](https://git.openi.org.cn/xfey):[NOTE](https://git.openi.org.cn/PCL_AutoML/AutoML/src/commit/62eed82bdd15b338ca09dfea26b5a8a77debd376/docs/notes/nas/Not%20All%20Operations%20Contribute%20Equally_%20Hierarchical%20Operation-adaptive%20Predictor%20for%20Neural%20Architecture%20Search.pdf) | |
|
|
|
| [Pi-NAS: Improving Neural Architecture Search by Reducing Supernet Training Consistency Shift](https://openaccess.thecvf.com/content/ICCV2021/papers/Peng_Pi-NAS_Improving_Neural_Architecture_Search_by_Reducing_Supernet_Training_Consistency_ICCV_2021_paper.pdf) | ICCV | [GitHub](https://github.com/Ernie1/Pi-NAS) | [XiangFei](https://git.openi.org.cn/xfey):[NOTE](https://git.openi.org.cn/PCL_AutoML/AutoML/src/commit/62eed82bdd15b338ca09dfea26b5a8a77debd376/docs/notes/nas/Pi-NAS_%20Improving%20Neural%20Architecture%20Search%20by%20Reducing%20Supernet%20Training%20Consistency%20Shift.pdf) | |
|
|
|
| [RANK-NOSH: Efficient Predictor-Based Architecture Search via Non-Uniform Successive Halving](https://openaccess.thecvf.com/content/ICCV2021/papers/Wang_RANK-NOSH_Efficient_Predictor-Based_Architecture_Search_via_Non-Uniform_Successive_Halving_ICCV_2021_paper.pdf) | ICCV | | [LeiZhang](https://git.openi.org.cn/isleizhang):[NOTE](https://git.openi.org.cn/PCL_AutoML/bbobenchmark/src/commit/55de41b8d14c0fd936629b25785d487dfd8a5f73/docs/NAS_paper_reading/RANK-NOSH_%20Efficient%20Predictor-Based%20Architecture%20Search%20via%20Non-Uniform%20Successive%20Halving.pdf) | |
|
|
|
| [Zen-NAS: A Zero-Shot NAS for High-Performance Deep Image Recognition](https://arxiv.org/abs/2102.01063) | ICCV | [Github](https://github.com/idstcv/ZenNAS) | | |
|
|
|
| [AutoFormer: Searching Transformers for Visual Recognition](https://arxiv.org/pdf/2107.00651.pdf) | ICCV | [GitHub](https://github.com/microsoft/AutoML) | | |
|
|
|
| [LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search](https://arxiv.org/abs/2104.14545) | CVPR | [GitHub](https://github.com/researchmm/LightTrack) | | |
|
|
|
| [Prioritized Architecture Sampling with Monto-Carlo Tree Search](https://arxiv.org/pdf/2103.11922.pdf) | CVPR | [GitHub](https://github.com/xiusu/NAS-Bench-Macro) | [XiangFei](https://git.openi.org.cn/xfey):[NOTE](https://git.openi.org.cn/PCL_AutoML/AutoML/src/commit/62eed82bdd15b338ca09dfea26b5a8a77debd376/docs/notes/nas/Prioritized%20Architecture%20Sampling%20with%20Monto-Carlo%20Tree%20Search.pdf) | |
|
|
|
| [One-Shot Neural Ensemble Architecture Search by Diversity-Guided Search Space Shrinking](https://arxiv.org/abs/2104.00597) | CVPR | [GitHub](https://github.com/researchmm/NEAS) | | |
|
|
|
| [DARTS-: Robustly Stepping out of Performance Collapse Without Indicators](https://openreview.net/pdf?id=KLH36ELmwIB) | ICLR | | | |
|
|
|
| [Zero-Cost Proxies for Lightweight NAS](https://openreview.net/pdf?id=0cmMMy8J5q) | ICLR | | | |
|
|
|
| [Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective](https://openreview.net/forum?id=Cnon5ezMHtu) | ICLR | [GitHub](https://github.com/VITA-Group/TENAS) | | |
|
|
|
| [DrNAS: Dirichlet Neural Architecture Search](https://openreview.net/forum?id=9FWas6YbmB3) | ICLR | [GitHub](https://github.com/xiangning-chen/DrNAS) | | |
|
|
|
| [Rethinking Architecture Selection in Differentiable NAS](https://openreview.net/forum?id=PKubaeJkw3) | ICLR | | | |
|
|
|
| [Evolving Reinforcement Learning Algorithms](https://openreview.net/forum?id=0XXpJ4OtjW) | ICLR | | | | | |
|
|
|
| Title | Venue | Code | Note | |
|
|
|
| :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :-----------: | :---------------------------------------------: | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | |
|
|
|
| [ProxyBO: Accelerating Neural Architecture Search via Bayesian Optimization with Zero-cost Proxies](https://arxiv.org/pdf/2110.10423.pdf) | ArXiv.2021.10 | | [LeiZhang](https://git.openi.org.cn/isleizhang):[NOTE](https://git.openi.org.cn/PCL_AutoML/bbobenchmark/src/commit/55de41b8d14c0fd936629b25785d487dfd8a5f73/docs/NAS_paper_reading/ProxyBO_%20Accelerating%20Neural%20Architecture%20Search%20via%20Bayesian%20Optimization%20with%20Zero-cost%20Proxies.pdf) | |
|
|
|
| [Approximate Neural Architecture Search via Operation Distribution Learning](https://arxiv.org/abs/2111.04670) | ArXiv.2021.08 | | [LeiZhang](https://git.openi.org.cn/isleizhang):[Note](https://git.openi.org.cn/PCL_AutoML/bbobenchmark/src/commit/55de41b8d14c0fd936629b25785d487dfd8a5f73/docs/NAS_paper_reading/Approximate%20Neural%20Architecture%20Search%20via%20Operation%20Distribution%20Learning%20.pdf) | |
|
|
|
| [Searching by Generating: Flexible and Efficient One-Shot NAS with Architecture Generator](https://openaccess.thecvf.com/content/CVPR2021/papers/Huang_Searching_by_Generating_Flexible_and_Efficient_One-Shot_NAS_With_Architecture_CVPR_2021_paper.pdf) | CVPR | [Github](https://github.com/eric8607242/SGNAS) | | |
|
|
|
| [Speedy Performance Estimation for Neural Architecture Search](https://arxiv.org/pdf/2006.04492.pdf) | NeurIPS | [Github](https://github.com/rubinxin/TSE) | [LeiZhang](https://git.openi.org.cn/isleizhang):[NOTE](https://git.openi.org.cn/PCL_AutoML/bbobenchmark/src/commit/55de41b8d14c0fd936629b25785d487dfd8a5f73/docs/NAS_paper_reading/Speedy%20Performance%20Estimation%20for%20Neural%20Architecture%20Search.pdf) | |
|
|
|
| [Generic Neural Architecture Search via Regression](https://proceedings.neurips.cc/paper/2021/file/aba53da2f6340a8b89dc96d09d0d0430-Paper.pdf) | NeurIPS | [Github](https://github.com/leeyeehoo/GenNAS) | [XiangFei](https://git.openi.org.cn/xfey):[NOTE](https://git.openi.org.cn/PCL_AutoML/AutoML/src/commit/62eed82bdd15b338ca09dfea26b5a8a77debd376/docs/notes/nas/Generic%20Neural%20Architecture%20Search%20via%20Regression.pdf) | |
|
|
|
| [Stronger NAS with Weaker Predictors](https://arxiv.org/abs/2102.10490) | NeurIPS | [Github](https://github.com/VITA-Group/WeakNAS) | [LeiZhang](https://git.openi.org.cn/isleizhang):[NOTE](https://git.openi.org.cn/PCL_AutoML/AutoML/src/branch/master/docs/notes/Stronger%20NAS%20with%20Weaker%20Predictors.pdf) | |
|
|
|
| [Learning Latent Architectural Distribution in Differentiable Neural Architecture Search via Variational Information Maximization](https://openaccess.thecvf.com/content/ICCV2021/html/Wang_Learning_Latent_Architectural_Distribution_in_Differentiable_Neural_Architecture_Search_via_ICCV_2021_paper.html) | ICCV | | [LeiZhang](https://git.openi.org.cn/isleizhang):[NOTE](https://git.openi.org.cn/PCL_AutoML/bbobenchmark/src/commit/55de41b8d14c0fd936629b25785d487dfd8a5f73/docs/NAS_paper_reading/Learning%20Latent%20Architectural%20Distribution%20in%20Differentiable%20Neural%20Architecture%20Search%20via%20Variational%20Information%20Maximization.pdf) | |
|
|
|
| [Not All Operations Contribute Equally: Hierarchical Operation-adaptive Predictor for Neural Architecture Search](https://openaccess.thecvf.com/content/ICCV2021/papers/Chen_Not_All_Operations_Contribute_Equally_Hierarchical_Operation-Adaptive_Predictor_for_Neural_ICCV_2021_paper.pdf) | ICCV | | [XiangFei](https://git.openi.org.cn/xfey):[NOTE](https://git.openi.org.cn/PCL_AutoML/AutoML/src/commit/62eed82bdd15b338ca09dfea26b5a8a77debd376/docs/notes/nas/Not%20All%20Operations%20Contribute%20Equally_%20Hierarchical%20Operation-adaptive%20Predictor%20for%20Neural%20Architecture%20Search.pdf) | |
|
|
|
| [Pi-NAS: Improving Neural Architecture Search by Reducing Supernet Training Consistency Shift](https://openaccess.thecvf.com/content/ICCV2021/papers/Peng_Pi-NAS_Improving_Neural_Architecture_Search_by_Reducing_Supernet_Training_Consistency_ICCV_2021_paper.pdf) | ICCV | [GitHub](https://github.com/Ernie1/Pi-NAS) | [XiangFei](https://git.openi.org.cn/xfey):[NOTE](https://git.openi.org.cn/PCL_AutoML/AutoML/src/commit/62eed82bdd15b338ca09dfea26b5a8a77debd376/docs/notes/nas/Pi-NAS_%20Improving%20Neural%20Architecture%20Search%20by%20Reducing%20Supernet%20Training%20Consistency%20Shift.pdf) | |
|
|
|
| [RANK-NOSH: Efficient Predictor-Based Architecture Search via Non-Uniform Successive Halving](https://openaccess.thecvf.com/content/ICCV2021/papers/Wang_RANK-NOSH_Efficient_Predictor-Based_Architecture_Search_via_Non-Uniform_Successive_Halving_ICCV_2021_paper.pdf) | ICCV | | [LeiZhang](https://git.openi.org.cn/isleizhang):[NOTE](https://git.openi.org.cn/PCL_AutoML/bbobenchmark/src/commit/55de41b8d14c0fd936629b25785d487dfd8a5f73/docs/NAS_paper_reading/RANK-NOSH_%20Efficient%20Predictor-Based%20Architecture%20Search%20via%20Non-Uniform%20Successive%20Halving.pdf) | |
|
|
|
| [Zen-NAS: A Zero-Shot NAS for High-Performance Deep Image Recognition](https://arxiv.org/abs/2102.01063) | ICCV | [Github](https://github.com/idstcv/ZenNAS) | | |
|
|
|
| [AutoFormer: Searching Transformers for Visual Recognition](https://arxiv.org/pdf/2107.00651.pdf) | ICCV | [GitHub](https://github.com/microsoft/AutoML) | | |
|
|
|
| [LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search](https://arxiv.org/abs/2104.14545) | CVPR | [GitHub](https://github.com/researchmm/LightTrack) | | |
|
|
|
| [Prioritized Architecture Sampling with Monto-Carlo Tree Search](https://arxiv.org/pdf/2103.11922.pdf) | CVPR | [GitHub](https://github.com/xiusu/NAS-Bench-Macro) | [XiangFei](https://git.openi.org.cn/xfey):[NOTE](https://git.openi.org.cn/PCL_AutoML/AutoML/src/commit/62eed82bdd15b338ca09dfea26b5a8a77debd376/docs/notes/nas/Prioritized%20Architecture%20Sampling%20with%20Monto-Carlo%20Tree%20Search.pdf) | |
|
|
|
| [One-Shot Neural Ensemble Architecture Search by Diversity-Guided Search Space Shrinking](https://arxiv.org/abs/2104.00597) | CVPR | [GitHub](https://github.com/researchmm/NEAS) | | |
|
|
|
| [DARTS-: Robustly Stepping out of Performance Collapse Without Indicators](https://openreview.net/pdf?id=KLH36ELmwIB) | ICLR | | | |
|
|
|
| [Zero-Cost Proxies for Lightweight NAS](https://openreview.net/pdf?id=0cmMMy8J5q) | ICLR | | | |
|
|
|
| [Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective](https://openreview.net/forum?id=Cnon5ezMHtu) | ICLR | [GitHub](https://github.com/VITA-Group/TENAS) | | |
|
|
|
| [DrNAS: Dirichlet Neural Architecture Search](https://openreview.net/forum?id=9FWas6YbmB3) | ICLR | [GitHub](https://github.com/xiangning-chen/DrNAS) | | |
|
|
|
| [Rethinking Architecture Selection in Differentiable NAS](https://openreview.net/forum?id=PKubaeJkw3) | ICLR | | | |
|
|
|
| [Evolving Reinforcement Learning Algorithms](https://openreview.net/forum?id=0XXpJ4OtjW) | ICLR | | | |
|
|
|
|
|
|
|
### 2020 |
|
|
|
|
|
|
|
|
|
|
|
| Title | Venue | Code | Note | |
|
|
|
| :----------------------------------------------------------- | :-----: | :----------------------------------------------------------: | ---- | |
|
|
|
| [Designing Network Design Spaces](https://arxiv.org/pdf/2003.13678.pdf) | CVPR | [GitHub](https://github.com/facebookresearch/pycls) | | |
|
|
|
| [Cream of the Crop: Distilling Prioritized Paths For One-Shot Neural Architecture Search](https://papers.nips.cc/paper/2020/file/d072677d210ac4c03ba046120f0802ec-Paper.pdf) | NeurIPS | [GitHub](https://github.com/microsoft/Cream) | | |
|
|
|
| [PyGlove: Symbolic Programming for Automated Machine Learning](https://proceedings.neurips.cc/paper/2020/file/012a91467f210472fab4e11359bbfef6-Paper.pdf) | NeurIPS | - | | |
|
|
|
| [Does Unsupervised Architecture Representation Learning Help Neural Architecture Search](https://arxiv.org/abs/2006.06936) | NeurIPS | [GitHub](https://github.com/MSU-MLSys-Lab/arch2vec) | | |
|
|
|
| [RandAugment: Practical Automated Data Augmentation with a Reduced Search Space](https://arxiv.org/abs/1909.13719) | NeurIPS | [GitHub](https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet) | | |
|
|
|
| [Delta-STN: Efficient Bilevel Optimization for Neural Networks using Structured Response Jacobians](https://arxiv.org/pdf/2010.13514.pdf) | NeurIPS | [GitHub](https://github.com/pomonam/Self-Tuning-Networks) | | |
|
|
|
| [A Study on Encodings for Neural Architecture Search](https://arxiv.org/abs/2007.04965) | NeurIPS | [GitHub](https://github.com/naszilla/naszilla) | | |
|
|
|
| [AutoBSS: An Efficient Algorithm for Block Stacking Style Search](https://proceedings.neurips.cc/paper/2020/file/747d3443e319a22747fbb873e8b2f9f2-Paper.pdf) | NeurIPS | | | |
|
|
|
| [Bridging the Gap between Sample-based and One-shot Neural Architecture Search with BONAS](https://proceedings.neurips.cc/paper/2020/file/13d4635deccc230c944e4ff6e03404b5-Paper.pdf) | NeurIPS | [GitHub](https://github.com/haolibai/APS-channel-search) | | |
|
|
|
| [Interstellar: Searching Recurrent Architecture for Knowledge Graph Embedding](https://proceedings.neurips.cc/paper/2020/file/722caafb4825ef5d8670710fa29087cf-Paper.pdf) | NeurIPS | | | |
|
|
|
| [Revisiting Parameter Sharing for Automatic Neural Channel Number Search](https://proceedings.neurips.cc/paper/2020/file/42cd63cb189c30ed03e42ce2c069566c-Paper.pdf) | NeurIPS | | | |
|
|
|
| [Learning Search Space Partition for Black-box Optimization using Monte Carlo Tree Search](https://arxiv.org/pdf/2007.00708.pdf) | NeurIPS | [GitHub](https://github.com/facebookresearch/LaMCTS) | | |
|
|
|
| [Neural Architecture Search using Deep Neural Networks and Monte Carlo Tree Search](https://arxiv.org/abs/1805.07440) | AAAI | [GitHub](https://github.com/linnanwang/AlphaX-NASBench101) | | |
|
|
|
| [Are Labels Necessary for Neural Architecture Search?](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123490766.pdf) | ECCV | - | | |
|
|
|
| [Single Path One-Shot Neural Architecture Search with Uniform Sampling](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123610528.pdf) | ECCV | - | | |
|
|
|
| [Neural Predictor for Neural Architecture Search](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123740647.pdf) | ECCV | - | | |
|
|
|
| [BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123520681.pdf) | ECCV | - | | |
|
|
|
| [BATS: Binary ArchitecTure Search](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123680307.pdf) | ECCV | - | | |
|
|
|
| [AttentionNAS: Spatiotemporal Attention Cell Search for Video Classification](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123530443.pdf) | ECCV | - | | |
|
|
|
| [Search What You Want: Barrier Panelty NAS for Mixed Precision Quantization](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123540001.pdf) | ECCV | - | | |
|
|
|
| [Angle-based Search Space Shrinking for Neural Architecture Search](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123630426.pdf) | ECCV | - | | |
|
|
|
| [Anti-Bandit Neural Architecture Search for Model Defense](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123580069.pdf) | ECCV | - | | |
|
|
|
| [TF-NAS: Rethinking Three Search Freedoms of Latency-Constrained Differentiable Neural Architecture Search](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123600120.pdf) | ECCV | [GitHub](https://github.com/AberHu/TF-NAS) | | |
|
|
|
| [Fair DARTS: Eliminating Unfair Advantages in Differentiable Architecture Search](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123600460.pdf) | ECCV | [GitHub](https://github.com/xiaomi-automl/FairDARTS) | | |
|
|
|
| [Off-Policy Reinforcement Learning for Efficient and Effective GAN Architecture Search](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123520171.pdf) | ECCV | - | | |
|
|
|
| [DA-NAS: Data Adapted Pruning for Efficient Neural Architecture Search](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123720579.pdf) | ECCV | - | | |
|
|
|
| [Optimizing Millions of Hyperparameters by Implicit Differentiation](https://arxiv.org/abs/1911.02590) | AISTATS | - | | |
|
|
|
| [Evolving Machine Learning Algorithms From Scratch](https://arxiv.org/pdf/2003.03384.pdf) | ICML | - | | |
|
|
|
| [Stabilizing Differentiable Architecture Search via Perturbation-based Regularization](https://arxiv.org/abs/2002.05283) | ICML | [GitHub](https://github.com/xiangning-chen/SmoothDARTS) | | |
|
|
|
| [NADS: Neural Architecture Distribution Search for Uncertainty Awareness](https://arxiv.org/pdf/2006.06646.pdf) | ICML | - | | |
|
|
|
| [Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training Data](https://arxiv.org/abs/1912.07768) | ICML | - | | |
|
|
|
| Neural Architecture Search in a Proxy Validation Loss Landscape | ICML | - | | |
|
|
|
| [UNAS: Differentiable Architecture Search Meets Reinforcement Learning](https://openaccess.thecvf.com/content_CVPR_2020/papers/Vahdat_UNAS_Differentiable_Architecture_Search_Meets_Reinforcement_Learning_CVPR_2020_paper.pdf) | CVPR | [GitHub](https://github.com/NVlabs/unas) | | |
|
|
|
| [MiLeNAS: Efficient Neural Architecture Search via Mixed-Level Reformulation](https://arxiv.org/pdf/2003.12238.pdf) | CVPR | [GitHub](https://github.com/chaoyanghe/MiLeNAS) | | |
|
|
|
| [A Semi-Supervised Assessor of Neural Architectures](https://openaccess.thecvf.com/content_CVPR_2020/papers/Tang_A_Semi-Supervised_Assessor_of_Neural_Architectures_CVPR_2020_paper.pdf) | CVPR | - | | |
|
|
|
| [Binarizing MobileNet via Evolution-based Searching](https://arxiv.org/abs/2005.06305) | CVPR | - | | |
|
|
|
| [Rethinking Performance Estimation in Neural Architecture Search](https://openaccess.thecvf.com/content_CVPR_2020/papers/Zheng_Rethinking_Performance_Estimation_in_Neural_Architecture_Search_CVPR_2020_paper.pdf) | CVPR | [GitHub](https://github.com/zhengxiawu/rethinking_performance_estimation_in_NAS) | | |
|
|
|
| [APQ: Joint Search for Network Architecture, Pruning and Quantization Policy](http://openaccess.thecvf.com/content_CVPR_2020/papers/Wang_APQ_Joint_Search_for_Network_Architecture_Pruning_and_Quantization_Policy_CVPR_2020_paper.pdf) | CVPR | [GitHub](https://github.com/mit-han-lab/apq) | | |
|
|
|
| [SGAS: Sequential Greedy Architecture Search](http://openaccess.thecvf.com/content_CVPR_2020/papers/Li_SGAS_Sequential_Greedy_Architecture_Search_CVPR_2020_paper.pdf) | CVPR | [Github](https://github.com/lightaime/sgas) | | |
|
|
|
| [Can Weight Sharing Outperform Random Architecture Search? An Investigation With TuNAS](http://openaccess.thecvf.com/content_CVPR_2020/papers/Bender_Can_Weight_Sharing_Outperform_Random_Architecture_Search_An_Investigation_With_CVPR_2020_paper.pdf) | CVPR | - | | |
|
|
|
| [FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions](https://arxiv.org/abs/2004.05565) | CVPR | [Github](https://github.com/facebookresearch/mobile-vision) | | |
|
|
|
| [AdversarialNAS: Adversarial Neural Architecture Search for GANs](https://arxiv.org/pdf/1912.02037.pdf) | CVPR | [Github](https://github.com/chengaopro/AdversarialNAS) | | |
|
|
|
| [When NAS Meets Robustness: In Search of Robust Architectures against Adversarial Attacks](https://arxiv.org/abs/1911.10695) | CVPR | [Github](https://github.com/gmh14/RobNets) | | |
|
|
|
| [Block-wisely Supervised Neural Architecture Search with Knowledge Distillation](https://www.xiaojun.ai/papers/CVPR2020_04676.pdf) | CVPR | [Github](https://github.com/changlin31/DNA) | | |
|
|
|
| [Overcoming Multi-Model Forgetting in One-Shot NAS with Diversity Maximization](https://www.xiaojun.ai/papers/cvpr-2020-zhang.pdf) | CVPR | [Github](https://github.com/MiaoZhang0525/NSAS_FOR_CVPR) | | |
|
|
|
| [Densely Connected Search Space for More Flexible Neural Architecture Search](https://arxiv.org/abs/1906.09607) | CVPR | [Github](https://github.com/JaminFong/DenseNAS) | | |
|
|
|
| [EfficientDet: Scalable and Efficient Object Detection](https://arxiv.org/abs/1911.09070) | CVPR | - | | |
|
|
|
| [NAS-BENCH-201: Extending the Scope of Reproducible Neural Architecture Search](https://openreview.net/forum?id=HJxyZkBKDr) | ICLR | [Github](https://github.com/D-X-Y/AutoDL-Projects) | | |
|
|
|
| [Understanding Architectures Learnt by Cell-based Neural Architecture Search](https://openreview.net/forum?id=BJxH22EKPS) | ICLR | [GitHub](https://github.com/shuyao95/Understanding-NAS) | | |
|
|
|
| [Evaluating The Search Phase of Neural Architecture Search](https://openreview.net/forum?id=H1loF2NFwr) | ICLR | | | |
|
|
|
| [AtomNAS: Fine-Grained End-to-End Neural Architecture Search](https://openreview.net/forum?id=BylQSxHFwr) | ICLR | [GitHub](https://github.com/meijieru/AtomNAS) | | |
|
|
|
| [Fast Neural Network Adaptation via Parameter Remapping and Architecture Search](https://openreview.net/forum?id=rklTmyBKPH) | ICLR | [GitHub](https://github.com/JaminFong/FNA) | | |
|
|
|
| [Once for All: Train One Network and Specialize it for Efficient Deployment](https://openreview.net/forum?id=HylxE1HKwS) | ICLR | [GitHub](https://github.com/mit-han-lab/once-for-all) | | |
|
|
|
| Efficient Transformer for Mobile Applications | ICLR | - | | |
|
|
|
| PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search | ICLR | [GitHub](https://github.com/yuhuixu1993/PC-DARTS) | | |
|
|
|
| Adversarial AutoAugment | ICLR | - | | |
|
|
|
| [NAS evaluation is frustratingly hard](https://arxiv.org/abs/1912.12522) | ICLR | [GitHub](https://github.com/antoyang/NAS-Benchmark) | | |
|
|
|
| [FasterSeg: Searching for Faster Real-time Semantic Segmentation](https://openreview.net/pdf?id=BJgqQ6NYvB) | ICLR | [GitHub](https://github.com/TAMU-VITA/FasterSeg) | | |
|
|
|
| [Computation Reallocation for Object Detection](https://openreview.net/forum?id=SkxLFaNKwB) | ICLR | - | | |
|
|
|
| Towards Fast Adaptation of Neural Architectures with Meta Learning | ICLR | - | | |
|
|
|
| AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures | ICLR | - | | |
|
|
|
| How to Own the NAS in Your Spare Time | ICLR | - | | |
|
|
|
| Title | Venue | Code | Note | |
|
|
|
| :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :-----: | :-------------------------------------------------------------------------------: | ---- | |
|
|
|
| [Designing Network Design Spaces](https://arxiv.org/pdf/2003.13678.pdf) | CVPR | [GitHub](https://github.com/facebookresearch/pycls) | | |
|
|
|
| [Cream of the Crop: Distilling Prioritized Paths For One-Shot Neural Architecture Search](https://papers.nips.cc/paper/2020/file/d072677d210ac4c03ba046120f0802ec-Paper.pdf) | NeurIPS | [GitHub](https://github.com/microsoft/Cream) | | |
|
|
|
| [PyGlove: Symbolic Programming for Automated Machine Learning](https://proceedings.neurips.cc/paper/2020/file/012a91467f210472fab4e11359bbfef6-Paper.pdf) | NeurIPS | - | | |
|
|
|
| [Does Unsupervised Architecture Representation Learning Help Neural Architecture Search](https://arxiv.org/abs/2006.06936) | NeurIPS | [GitHub](https://github.com/MSU-MLSys-Lab/arch2vec) | | |
|
|
|
| [RandAugment: Practical Automated Data Augmentation with a Reduced Search Space](https://arxiv.org/abs/1909.13719) | NeurIPS | [GitHub](https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet) | | |
|
|
|
| [Delta-STN: Efficient Bilevel Optimization for Neural Networks using Structured Response Jacobians](https://arxiv.org/pdf/2010.13514.pdf) | NeurIPS | [GitHub](https://github.com/pomonam/Self-Tuning-Networks) | | |
|
|
|
| [A Study on Encodings for Neural Architecture Search](https://arxiv.org/abs/2007.04965) | NeurIPS | [GitHub](https://github.com/naszilla/naszilla) | | |
|
|
|
| [AutoBSS: An Efficient Algorithm for Block Stacking Style Search](https://proceedings.neurips.cc/paper/2020/file/747d3443e319a22747fbb873e8b2f9f2-Paper.pdf) | NeurIPS | | | |
|
|
|
| [Bridging the Gap between Sample-based and One-shot Neural Architecture Search with BONAS](https://proceedings.neurips.cc/paper/2020/file/13d4635deccc230c944e4ff6e03404b5-Paper.pdf) | NeurIPS | [GitHub](https://github.com/haolibai/APS-channel-search) | | |
|
|
|
| [Interstellar: Searching Recurrent Architecture for Knowledge Graph Embedding](https://proceedings.neurips.cc/paper/2020/file/722caafb4825ef5d8670710fa29087cf-Paper.pdf) | NeurIPS | | | |
|
|
|
| [Revisiting Parameter Sharing for Automatic Neural Channel Number Search](https://proceedings.neurips.cc/paper/2020/file/42cd63cb189c30ed03e42ce2c069566c-Paper.pdf) | NeurIPS | | | |
|
|
|
| [Learning Search Space Partition for Black-box Optimization using Monte Carlo Tree Search](https://arxiv.org/pdf/2007.00708.pdf) | NeurIPS | [GitHub](https://github.com/facebookresearch/LaMCTS) | | |
|
|
|
| [Neural Architecture Search using Deep Neural Networks and Monte Carlo Tree Search](https://arxiv.org/abs/1805.07440) | AAAI | [GitHub](https://github.com/linnanwang/AlphaX-NASBench101) | | |
|
|
|
| [Are Labels Necessary for Neural Architecture Search?](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123490766.pdf) | ECCV | - | | |
|
|
|
| [Single Path One-Shot Neural Architecture Search with Uniform Sampling](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123610528.pdf) | ECCV | - | | |
|
|
|
| [Neural Predictor for Neural Architecture Search](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123740647.pdf) | ECCV | - | | |
|
|
|
| [BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123520681.pdf) | ECCV | - | | |
|
|
|
| [BATS: Binary ArchitecTure Search](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123680307.pdf) | ECCV | - | | |
|
|
|
| [AttentionNAS: Spatiotemporal Attention Cell Search for Video Classification](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123530443.pdf) | ECCV | - | | |
|
|
|
| [Search What You Want: Barrier Panelty NAS for Mixed Precision Quantization](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123540001.pdf) | ECCV | - | | |
|
|
|
| [Angle-based Search Space Shrinking for Neural Architecture Search](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123630426.pdf) | ECCV | - | | |
|
|
|
| [Anti-Bandit Neural Architecture Search for Model Defense](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123580069.pdf) | ECCV | - | | |
|
|
|
| [TF-NAS: Rethinking Three Search Freedoms of Latency-Constrained Differentiable Neural Architecture Search](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123600120.pdf) | ECCV | [GitHub](https://github.com/AberHu/TF-NAS) | | |
|
|
|
| [Fair DARTS: Eliminating Unfair Advantages in Differentiable Architecture Search](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123600460.pdf) | ECCV | [GitHub](https://github.com/xiaomi-automl/FairDARTS) | | |
|
|
|
| [Off-Policy Reinforcement Learning for Efficient and Effective GAN Architecture Search](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123520171.pdf) | ECCV | - | | |
|
|
|
| [DA-NAS: Data Adapted Pruning for Efficient Neural Architecture Search](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123720579.pdf) | ECCV | - | | |
|
|
|
| [Optimizing Millions of Hyperparameters by Implicit Differentiation](https://arxiv.org/abs/1911.02590) | AISTATS | - | | |
|
|
|
| [Evolving Machine Learning Algorithms From Scratch](https://arxiv.org/pdf/2003.03384.pdf) | ICML | - | | |
|
|
|
| [Stabilizing Differentiable Architecture Search via Perturbation-based Regularization](https://arxiv.org/abs/2002.05283) | ICML | [GitHub](https://github.com/xiangning-chen/SmoothDARTS) | | |
|
|
|
| [NADS: Neural Architecture Distribution Search for Uncertainty Awareness](https://arxiv.org/pdf/2006.06646.pdf) | ICML | - | | |
|
|
|
| [Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training Data](https://arxiv.org/abs/1912.07768) | ICML | - | | |
|
|
|
| Neural Architecture Search in a Proxy Validation Loss Landscape | ICML | - | | |
|
|
|
| [UNAS: Differentiable Architecture Search Meets Reinforcement Learning](https://openaccess.thecvf.com/content_CVPR_2020/papers/Vahdat_UNAS_Differentiable_Architecture_Search_Meets_Reinforcement_Learning_CVPR_2020_paper.pdf) | CVPR | [GitHub](https://github.com/NVlabs/unas) | | |
|
|
|
| [MiLeNAS: Efficient Neural Architecture Search via Mixed-Level Reformulation](https://arxiv.org/pdf/2003.12238.pdf) | CVPR | [GitHub](https://github.com/chaoyanghe/MiLeNAS) | | |
|
|
|
| [A Semi-Supervised Assessor of Neural Architectures](https://openaccess.thecvf.com/content_CVPR_2020/papers/Tang_A_Semi-Supervised_Assessor_of_Neural_Architectures_CVPR_2020_paper.pdf) | CVPR | - | | |
|
|
|
| [Binarizing MobileNet via Evolution-based Searching](https://arxiv.org/abs/2005.06305) | CVPR | - | | |
|
|
|
| [Rethinking Performance Estimation in Neural Architecture Search](https://openaccess.thecvf.com/content_CVPR_2020/papers/Zheng_Rethinking_Performance_Estimation_in_Neural_Architecture_Search_CVPR_2020_paper.pdf) | CVPR | [GitHub](https://github.com/zhengxiawu/rethinking_performance_estimation_in_NAS) | | |
|
|
|
| [APQ: Joint Search for Network Architecture, Pruning and Quantization Policy](http://openaccess.thecvf.com/content_CVPR_2020/papers/Wang_APQ_Joint_Search_for_Network_Architecture_Pruning_and_Quantization_Policy_CVPR_2020_paper.pdf) | CVPR | [GitHub](https://github.com/mit-han-lab/apq) | | |
|
|
|
| [SGAS: Sequential Greedy Architecture Search](http://openaccess.thecvf.com/content_CVPR_2020/papers/Li_SGAS_Sequential_Greedy_Architecture_Search_CVPR_2020_paper.pdf) | CVPR | [Github](https://github.com/lightaime/sgas) | | |
|
|
|
| [Can Weight Sharing Outperform Random Architecture Search? An Investigation With TuNAS](http://openaccess.thecvf.com/content_CVPR_2020/papers/Bender_Can_Weight_Sharing_Outperform_Random_Architecture_Search_An_Investigation_With_CVPR_2020_paper.pdf) | CVPR | - | | |
|
|
|
| [FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions](https://arxiv.org/abs/2004.05565) | CVPR | [Github](https://github.com/facebookresearch/mobile-vision) | | |
|
|
|
| [AdversarialNAS: Adversarial Neural Architecture Search for GANs](https://arxiv.org/pdf/1912.02037.pdf) | CVPR | [Github](https://github.com/chengaopro/AdversarialNAS) | | |
|
|
|
| [When NAS Meets Robustness: In Search of Robust Architectures against Adversarial Attacks](https://arxiv.org/abs/1911.10695) | CVPR | [Github](https://github.com/gmh14/RobNets) | | |
|
|
|
| [Block-wisely Supervised Neural Architecture Search with Knowledge Distillation](https://www.xiaojun.ai/papers/CVPR2020_04676.pdf) | CVPR | [Github](https://github.com/changlin31/DNA) | | |
|
|
|
| [Overcoming Multi-Model Forgetting in One-Shot NAS with Diversity Maximization](https://www.xiaojun.ai/papers/cvpr-2020-zhang.pdf) | CVPR | [Github](https://github.com/MiaoZhang0525/NSAS_FOR_CVPR) | | |
|
|
|
| [Densely Connected Search Space for More Flexible Neural Architecture Search](https://arxiv.org/abs/1906.09607) | CVPR | [Github](https://github.com/JaminFong/DenseNAS) | | |
|
|
|
| [EfficientDet: Scalable and Efficient Object Detection](https://arxiv.org/abs/1911.09070) | CVPR | - | | |
|
|
|
| [NAS-BENCH-201: Extending the Scope of Reproducible Neural Architecture Search](https://openreview.net/forum?id=HJxyZkBKDr) | ICLR | [Github](https://github.com/D-X-Y/AutoDL-Projects) | | |
|
|
|
| [Understanding Architectures Learnt by Cell-based Neural Architecture Search](https://openreview.net/forum?id=BJxH22EKPS) | ICLR | [GitHub](https://github.com/shuyao95/Understanding-NAS) | | |
|
|
|
| [Evaluating The Search Phase of Neural Architecture Search](https://openreview.net/forum?id=H1loF2NFwr) | ICLR | | | |
|
|
|
| [AtomNAS: Fine-Grained End-to-End Neural Architecture Search](https://openreview.net/forum?id=BylQSxHFwr) | ICLR | [GitHub](https://github.com/meijieru/AtomNAS) | | |
|
|
|
| [Fast Neural Network Adaptation via Parameter Remapping and Architecture Search](https://openreview.net/forum?id=rklTmyBKPH) | ICLR | [GitHub](https://github.com/JaminFong/FNA) | | |
|
|
|
| [Once for All: Train One Network and Specialize it for Efficient Deployment](https://openreview.net/forum?id=HylxE1HKwS) | ICLR | [GitHub](https://github.com/mit-han-lab/once-for-all) | | |
|
|
|
| Efficient Transformer for Mobile Applications | ICLR | - | | |
|
|
|
| PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search | ICLR | [GitHub](https://github.com/yuhuixu1993/PC-DARTS) | | |
|
|
|
| Adversarial AutoAugment | ICLR | - | | |
|
|
|
| [NAS evaluation is frustratingly hard](https://arxiv.org/abs/1912.12522) | ICLR | [GitHub](https://github.com/antoyang/NAS-Benchmark) | | |
|
|
|
| [FasterSeg: Searching for Faster Real-time Semantic Segmentation](https://openreview.net/pdf?id=BJgqQ6NYvB) | ICLR | [GitHub](https://github.com/TAMU-VITA/FasterSeg) | | |
|
|
|
| [Computation Reallocation for Object Detection](https://openreview.net/forum?id=SkxLFaNKwB) | ICLR | - | | |
|
|
|
| Towards Fast Adaptation of Neural Architectures with Meta Learning | ICLR | - | | |
|
|
|
| AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures | ICLR | - | | |
|
|
|
| How to Own the NAS in Your Spare Time | ICLR | - | | |
|
|
|
|
|
|
|
### 2019 |
|
|
|
|
|
|
|
| Title | Venue | Code | Note | |
|
|
|
| :----------------------------------------------------------- | :-----: | :----------------------------------------------------------: | ---- | |
|
|
|
| [Self-Tuning Networks: Bilevel Optimization of Hyperparameters using Structured Best-Response Functions](https://arxiv.org/abs/1903.03088) | ICLR | - | | |
|
|
|
| [DATA: Differentiable ArchiTecture Approximation](http://papers.nips.cc/paper/8374-data-differentiable-architecture-approximation) | NeurIPS | - | | |
|
|
|
| Random Search and Reproducibility for Neural Architecture Search | UAI | [GitHub](https://github.com/D-X-Y/NAS-Projects/blob/master/scripts-search/algos/RANDOM-NAS.sh) | | |
|
|
|
| [Improved Differentiable Architecture Search for Language Modeling and Named Entity Recognition](https://www.aclweb.org/anthology/D19-1367.pdf/) | EMNLP | - | | |
|
|
|
| [Continual and Multi-Task Architecture Search](https://www.aclweb.org/anthology/P19-1185.pdf) | ACL | - | | |
|
|
|
| Progressive Differentiable Architecture Search: Bridging the Depth Gap Between Search and Evaluation | ICCV | - | | |
|
|
|
| Multinomial Distribution Learning for Effective Neural Architecture Search | ICCV | - | | |
|
|
|
| Searching for MobileNetV3 | ICCV | - | | |
|
|
|
| [Multinomial Distribution Learning for Effective Neural Architecture Search](http://openaccess.thecvf.com/content_ICCV_2019/papers/Zheng_Multinomial_Distribution_Learning_for_Effective_Neural_Architecture_Search_ICCV_2019_paper.pdf) | ICCV | [GitHub](https://github.com/tanglang96/MDENAS) | | |
|
|
|
| [Fast and Practical Neural Architecture Search](http://openaccess.thecvf.com/content_ICCV_2019/papers/Cui_Fast_and_Practical_Neural_Architecture_Search_ICCV_2019_paper.pdf) | ICCV | | | |
|
|
|
| [Teacher Guided Architecture Search](http://openaccess.thecvf.com/content_ICCV_2019/papers/Bashivan_Teacher_Guided_Architecture_Search_ICCV_2019_paper.pdf) | ICCV | - | | |
|
|
|
| [AutoDispNet: Improving Disparity Estimation With AutoML](http://openaccess.thecvf.com/content_ICCV_2019/papers/Saikia_AutoDispNet_Improving_Disparity_Estimation_With_AutoML_ICCV_2019_paper.pdf) | ICCV | - | | |
|
|
|
| [Resource Constrained Neural Network Architecture Search: Will a Submodularity Assumption Help?](http://openaccess.thecvf.com/content_ICCV_2019/papers/Xiong_Resource_Constrained_Neural_Network_Architecture_Search_Will_a_Submodularity_Assumption_ICCV_2019_paper.pdf) | ICCV | - | | |
|
|
|
| [One-Shot Neural Architecture Search via Self-Evaluated Template Network](https://arxiv.org/abs/1910.05733) | ICCV | [Github](https://github.com/D-X-Y/NAS-Projects) | | |
|
|
|
| [Evolving Space-Time Neural Architectures for Videos](https://arxiv.org/abs/1811.10636) | ICCV | [GitHub](https://sites.google.com/view/evanet-video) | | |
|
|
|
| [AutoGAN: Neural Architecture Search for Generative Adversarial Networks](https://arxiv.org/pdf/1908.03835.pdf) | ICCV | [github](https://github.com/TAMU-VITA/AutoGAN) | | |
|
|
|
| [Discovering Neural Wirings](https://arxiv.org/pdf/1906.00586.pdf) | NeurIPS | [Github](https://github.com/allenai/dnw) | | |
|
|
|
| [Towards modular and programmable architecture search](https://arxiv.org/abs/1909.13404) | NeurIPS | [Github](https://github.com/negrinho/deep_architect) | | |
|
|
|
| [Network Pruning via Transformable Architecture Search](https://arxiv.org/abs/1905.09717) | NeurIPS | [Github](https://github.com/D-X-Y/NAS-Projects) | | |
|
|
|
| [Deep Active Learning with a NeuralArchitecture Search](https://arxiv.org/pdf/1811.07579.pdf) | NeurIPS | - | | |
|
|
|
| DetNAS: Backbone Search for ObjectDetection | NeurIPS | - | | |
|
|
|
| SpArSe: Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollers | NeurIPS | - | | |
|
|
|
| [Efficient Forward Architecture Search ](https://arxiv.org/abs/1905.13360) | NeurIPS | [Github](https://github.com/microsoft/petridishnn) | | |
|
|
|
| Efficient Neural ArchitectureTransformation Search in Channel-Level for Object Detection | NeurIPS | - | | |
|
|
|
| XNAS: Neural Architecture Search with Expert Advice | NeurIPS | - | | |
|
|
|
| [DARTS: Differentiable Architecture Search](https://arxiv.org/abs/1806.09055) | ICLR | [github](https://github.com/quark0/darts) | | |
|
|
|
| [ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware](https://openreview.net/pdf?id=HylVB3AqYm) | ICLR | [github](https://github.com/MIT-HAN-LAB/ProxylessNAS) | | |
|
|
|
| [Graph HyperNetworks for Neural Architecture Search](https://arxiv.org/pdf/1810.05749.pdf) | ICLR | - | | |
|
|
|
| [Learnable Embedding Space for Efficient Neural Architecture Compression](https://openreview.net/forum?id=S1xLN3C9YX) | ICLR | [github](https://github.com/Friedrich1006/ESNAC) | | |
|
|
|
| [Efficient Multi-Objective Neural Architecture Search via Lamarckian Evolution](https://arxiv.org/abs/1804.09081) | ICLR | - | | |
|
|
|
| [SNAS: stochastic neural architecture search](https://openreview.net/pdf?id=rylqooRqK7) | ICLR | - | | |
|
|
|
| [NetTailor: Tuning the Architecture, Not Just the Weights](https://arxiv.org/abs/1907.00274) | CVPR | [Github](https://github.com/pedro-morgado/nettailor) | | |
|
|
|
| [Searching for A Robust Neural Architecture in Four GPU Hours](http://xuanyidong.com/publication/gradient-based-diff-sampler/) | CVPR | [Github](https://github.com/D-X-Y/NAS-Projects) | | |
|
|
|
| [ChamNet: Towards Efficient Network Design through Platform-Aware Model Adaptation](http://openaccess.thecvf.com/content_CVPR_2019/papers/Dai_ChamNet_Towards_Efficient_Network_Design_Through_Platform-Aware_Model_Adaptation_CVPR_2019_paper.pdf) | CVPR | - | | |
|
|
|
| [Partial Order Pruning: for Best Speed/Accuracy Trade-off in Neural Architecture Search](https://arxiv.org/pdf/1903.03777.pdf) | CVPR | [github](https://github.com/lixincn2015/Partial-Order-Pruning) | | |
|
|
|
| [FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search](https://arxiv.org/abs/1812.03443) | CVPR | - | | |
|
|
|
| [RENAS: Reinforced Evolutionary Neural Architecture Search ](https://arxiv.org/abs/1808.00193) | CVPR | - | | |
|
|
|
| [Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation](https://arxiv.org/pdf/1901.02985.pdf) | CVPR | [GitHub](https://github.com/tensorflow/models/tree/master/research/deeplab) | | |
|
|
|
| [MnasNet: Platform-Aware Neural Architecture Search for Mobile](https://arxiv.org/abs/1807.11626) | CVPR | [Github](https://github.com/AnjieZheng/MnasNet-PyTorch) | | |
|
|
|
| [MFAS: Multimodal Fusion Architecture Search](https://arxiv.org/pdf/1903.06496.pdf) | CVPR | - | | |
|
|
|
| [A Neurobiological Evaluation Metric for Neural Network Model Search](https://arxiv.org/pdf/1805.10726.pdf) | CVPR | - | | |
|
|
|
| [Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells](https://arxiv.org/abs/1810.10804) | CVPR | - | | |
|
|
|
| Customizable Architecture Search for Semantic Segmentation | CVPR | - | | |
|
|
|
| [Regularized Evolution for Image Classifier Architecture Search](https://arxiv.org/pdf/1802.01548.pdf) | AAAI | - | | |
|
|
|
| AutoAugment: Learning Augmentation Policies from Data | CVPR | - | | |
|
|
|
| Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules | ICML | - | | |
|
|
|
| [The Evolved Transformer](https://arxiv.org/pdf/1901.11117.pdf) | ICML | [Github](https://github.com/tensorflow/tensor2tensor/blob/master/tensor2tensor/models/evolved_transformer.py) | | |
|
|
|
| EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks | ICML | - | | |
|
|
|
| [NAS-Bench-101: Towards Reproducible Neural Architecture Search](https://arxiv.org/abs/1902.09635) | ICML | [Github](https://github.com/google-research/nasbench) | | |
|
|
|
| [On Network Design Spaces for Visual Recognition](https://arxiv.org/abs/1905.13214) | ICCV | [Github](https://github.com/facebookresearch/nds) | | |
|
|
|
| Title | Venue | Code | Note | |
|
|
|
| :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :-----: | :--------------------------------------------------------------------------------------------------------: | ---- | |
|
|
|
| [Self-Tuning Networks: Bilevel Optimization of Hyperparameters using Structured Best-Response Functions](https://arxiv.org/abs/1903.03088) | ICLR | - | | |
|
|
|
| [DATA: Differentiable ArchiTecture Approximation](http://papers.nips.cc/paper/8374-data-differentiable-architecture-approximation) | NeurIPS | - | | |
|
|
|
| Random Search and Reproducibility for Neural Architecture Search | UAI | [GitHub](https://github.com/D-X-Y/NAS-Projects/blob/master/scripts-search/algos/RANDOM-NAS.sh) | | |
|
|
|
| [Improved Differentiable Architecture Search for Language Modeling and Named Entity Recognition](https://www.aclweb.org/anthology/D19-1367.pdf/) | EMNLP | - | | |
|
|
|
| [Continual and Multi-Task Architecture Search](https://www.aclweb.org/anthology/P19-1185.pdf) | ACL | - | | |
|
|
|
| Progressive Differentiable Architecture Search: Bridging the Depth Gap Between Search and Evaluation | ICCV | - | | |
|
|
|
| Multinomial Distribution Learning for Effective Neural Architecture Search | ICCV | - | | |
|
|
|
| Searching for MobileNetV3 | ICCV | - | | |
|
|
|
| [Multinomial Distribution Learning for Effective Neural Architecture Search](http://openaccess.thecvf.com/content_ICCV_2019/papers/Zheng_Multinomial_Distribution_Learning_for_Effective_Neural_Architecture_Search_ICCV_2019_paper.pdf) | ICCV | [GitHub](https://github.com/tanglang96/MDENAS) | | |
|
|
|
| [Fast and Practical Neural Architecture Search](http://openaccess.thecvf.com/content_ICCV_2019/papers/Cui_Fast_and_Practical_Neural_Architecture_Search_ICCV_2019_paper.pdf) | ICCV | | | |
|
|
|
| [Teacher Guided Architecture Search](http://openaccess.thecvf.com/content_ICCV_2019/papers/Bashivan_Teacher_Guided_Architecture_Search_ICCV_2019_paper.pdf) | ICCV | - | | |
|
|
|
| [AutoDispNet: Improving Disparity Estimation With AutoML](http://openaccess.thecvf.com/content_ICCV_2019/papers/Saikia_AutoDispNet_Improving_Disparity_Estimation_With_AutoML_ICCV_2019_paper.pdf) | ICCV | - | | |
|
|
|
| [Resource Constrained Neural Network Architecture Search: Will a Submodularity Assumption Help?](http://openaccess.thecvf.com/content_ICCV_2019/papers/Xiong_Resource_Constrained_Neural_Network_Architecture_Search_Will_a_Submodularity_Assumption_ICCV_2019_paper.pdf) | ICCV | - | | |
|
|
|
| [One-Shot Neural Architecture Search via Self-Evaluated Template Network](https://arxiv.org/abs/1910.05733) | ICCV | [Github](https://github.com/D-X-Y/NAS-Projects) | | |
|
|
|
| [Evolving Space-Time Neural Architectures for Videos](https://arxiv.org/abs/1811.10636) | ICCV | [GitHub](https://sites.google.com/view/evanet-video) | | |
|
|
|
| [AutoGAN: Neural Architecture Search for Generative Adversarial Networks](https://arxiv.org/pdf/1908.03835.pdf) | ICCV | [github](https://github.com/TAMU-VITA/AutoGAN) | | |
|
|
|
| [Discovering Neural Wirings](https://arxiv.org/pdf/1906.00586.pdf) | NeurIPS | [Github](https://github.com/allenai/dnw) | | |
|
|
|
| [Towards modular and programmable architecture search](https://arxiv.org/abs/1909.13404) | NeurIPS | [Github](https://github.com/negrinho/deep_architect) | | |
|
|
|
| [Network Pruning via Transformable Architecture Search](https://arxiv.org/abs/1905.09717) | NeurIPS | [Github](https://github.com/D-X-Y/NAS-Projects) | | |
|
|
|
| [Deep Active Learning with a NeuralArchitecture Search](https://arxiv.org/pdf/1811.07579.pdf) | NeurIPS | - | | |
|
|
|
| DetNAS: Backbone Search for ObjectDetection | NeurIPS | - | | |
|
|
|
| SpArSe: Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollers | NeurIPS | - | | |
|
|
|
| [Efficient Forward Architecture Search ](https://arxiv.org/abs/1905.13360) | NeurIPS | [Github](https://github.com/microsoft/petridishnn) | | |
|
|
|
| Efficient Neural ArchitectureTransformation Search in Channel-Level for Object Detection | NeurIPS | - | | |
|
|
|
| XNAS: Neural Architecture Search with Expert Advice | NeurIPS | - | | |
|
|
|
| [DARTS: Differentiable Architecture Search](https://arxiv.org/abs/1806.09055) | ICLR | [github](https://github.com/quark0/darts) | | |
|
|
|
| [ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware](https://openreview.net/pdf?id=HylVB3AqYm) | ICLR | [github](https://github.com/MIT-HAN-LAB/ProxylessNAS) | | |
|
|
|
| [Graph HyperNetworks for Neural Architecture Search](https://arxiv.org/pdf/1810.05749.pdf) | ICLR | - | | |
|
|
|
| [Learnable Embedding Space for Efficient Neural Architecture Compression](https://openreview.net/forum?id=S1xLN3C9YX) | ICLR | [github](https://github.com/Friedrich1006/ESNAC) | | |
|
|
|
| [Efficient Multi-Objective Neural Architecture Search via Lamarckian Evolution](https://arxiv.org/abs/1804.09081) | ICLR | - | | |
|
|
|
| [SNAS: stochastic neural architecture search](https://openreview.net/pdf?id=rylqooRqK7) | ICLR | - | | |
|
|
|
| [NetTailor: Tuning the Architecture, Not Just the Weights](https://arxiv.org/abs/1907.00274) | CVPR | [Github](https://github.com/pedro-morgado/nettailor) | | |
|
|
|
| [Searching for A Robust Neural Architecture in Four GPU Hours](http://xuanyidong.com/publication/gradient-based-diff-sampler/) | CVPR | [Github](https://github.com/D-X-Y/NAS-Projects) | | |
|
|
|
| [ChamNet: Towards Efficient Network Design through Platform-Aware Model Adaptation](http://openaccess.thecvf.com/content_CVPR_2019/papers/Dai_ChamNet_Towards_Efficient_Network_Design_Through_Platform-Aware_Model_Adaptation_CVPR_2019_paper.pdf) | CVPR | - | | |
|
|
|
| [Partial Order Pruning: for Best Speed/Accuracy Trade-off in Neural Architecture Search](https://arxiv.org/pdf/1903.03777.pdf) | CVPR | [github](https://github.com/lixincn2015/Partial-Order-Pruning) | | |
|
|
|
| [FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search](https://arxiv.org/abs/1812.03443) | CVPR | - | | |
|
|
|
| [RENAS: Reinforced Evolutionary Neural Architecture Search ](https://arxiv.org/abs/1808.00193) | CVPR | - | | |
|
|
|
| [Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation](https://arxiv.org/pdf/1901.02985.pdf) | CVPR | [GitHub](https://github.com/tensorflow/models/tree/master/research/deeplab) | | |
|
|
|
| [MnasNet: Platform-Aware Neural Architecture Search for Mobile](https://arxiv.org/abs/1807.11626) | CVPR | [Github](https://github.com/AnjieZheng/MnasNet-PyTorch) | | |
|
|
|
| [MFAS: Multimodal Fusion Architecture Search](https://arxiv.org/pdf/1903.06496.pdf) | CVPR | - | | |
|
|
|
| [A Neurobiological Evaluation Metric for Neural Network Model Search](https://arxiv.org/pdf/1805.10726.pdf) | CVPR | - | | |
|
|
|
| [Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells](https://arxiv.org/abs/1810.10804) | CVPR | - | | |
|
|
|
| Customizable Architecture Search for Semantic Segmentation | CVPR | - | | |
|
|
|
| [Regularized Evolution for Image Classifier Architecture Search](https://arxiv.org/pdf/1802.01548.pdf) | AAAI | - | | |
|
|
|
| AutoAugment: Learning Augmentation Policies from Data | CVPR | - | | |
|
|
|
| Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules | ICML | - | | |
|
|
|
| [The Evolved Transformer](https://arxiv.org/pdf/1901.11117.pdf) | ICML | [Github](https://github.com/tensorflow/tensor2tensor/blob/master/tensor2tensor/models/evolved_transformer.py) | | |
|
|
|
| EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks | ICML | - | | |
|
|
|
| [NAS-Bench-101: Towards Reproducible Neural Architecture Search](https://arxiv.org/abs/1902.09635) | ICML | [Github](https://github.com/google-research/nasbench) | | |
|
|
|
| [On Network Design Spaces for Visual Recognition](https://arxiv.org/abs/1905.13214) | ICCV | [Github](https://github.com/facebookresearch/nds) | | |
|
|
|
|
|
|
|
### 2018 |
|
|
|
|
|
|
|
| Title | Venue | Code | Note | |
|
|
|
| :----------------------------------------------------------- | :-----: | :----------------------------------------------------------: | ---- | |
|
|
|
| Towards Automatically-Tuned Deep Neural Networks | BOOK | [GitHub](https://github.com/automl/Auto-PyTorch) | | |
|
|
|
| [NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications](https://arxiv.org/pdf/1804.03230.pdf) | ECCV | [github](https://github.com/denru01/netadapt) | | |
|
|
|
| [Efficient Architecture Search by Network Transformation](https://arxiv.org/pdf/1707.04873.pdf) | AAAI | [github](https://github.com/han-cai/EAS) | | |
|
|
|
| [Learning Transferable Architectures for Scalable Image Recognition](http://openaccess.thecvf.com/content_cvpr_2018/papers/Zoph_Learning_Transferable_Architectures_CVPR_2018_paper.pdf) | CVPR | [github](https://github.com/tensorflow/models/tree/master/research/slim/nets/nasnet) | | |
|
|
|
| [N2N learning: Network to Network Compression via Policy Gradient Reinforcement Learning](https://openreview.net/forum?id=B1hcZZ-AW) | ICLR | - | | |
|
|
|
| [A Flexible Approach to Automated RNN Architecture Generation](https://openreview.net/forum?id=SkOb1Fl0Z) | ICLR | - | | |
|
|
|
| [Practical Block-wise Neural Network Architecture Generation](http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhong_Practical_Block-Wise_Neural_CVPR_2018_paper.pdf) | CVPR | - | | |
|
|
|
| [Path-Level Network Transformation for Efficient Architecture Search](https://arxiv.org/abs/1806.02639) | ICML | [github](https://github.com/han-cai/PathLevel-EAS) | | |
|
|
|
| [Hierarchical Representations for Efficient Architecture Search](https://openreview.net/forum?id=BJQRKzbA-) | ICLR | - | | |
|
|
|
| [Understanding and Simplifying One-Shot Architecture Search](http://proceedings.mlr.press/v80/bender18a/bender18a.pdf) | ICML | - | | |
|
|
|
| [SMASH: One-Shot Model Architecture Search through HyperNetworks](https://arxiv.org/pdf/1708.05344.pdf) | ICLR | [github](https://github.com/ajbrock/SMASH) | | |
|
|
|
| [Neural Architecture Optimization](https://arxiv.org/pdf/1808.07233.pdf) | NeurIPS | [github](https://github.com/renqianluo/NAO) | | |
|
|
|
| [Searching for efficient multi-scale architectures for dense image prediction](https://papers.nips.cc/paper/8087-searching-for-efficient-multi-scale-architectures-for-dense-image-prediction.pdf) | NeurIPS | - | | |
|
|
|
| [Progressive Neural Architecture Search](http://openaccess.thecvf.com/content_ECCV_2018/papers/Chenxi_Liu_Progressive_Neural_Architecture_ECCV_2018_paper.pdf) | ECCV | [github](https://github.com/chenxi116/PNASNet) | | |
|
|
|
| [Neural Architecture Search with Bayesian Optimisation and Optimal Transport](https://arxiv.org/pdf/1802.07191.pdf) | NeurIPS | [github](https://github.com/kirthevasank/nasbot) | | |
|
|
|
| [Differentiable Neural Network Architecture Search](https://openreview.net/pdf?id=BJ-MRKkwG) | ICLR-W | - | | |
|
|
|
| [Accelerating Neural Architecture Search using Performance Prediction](https://arxiv.org/abs/1705.10823) | ICLR-W | - | | |
|
|
|
|
|
|
|
|
|
|
|
| Title | Venue | Code | Note | |
|
|
|
| :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :-----: | :-------------------------------------------------------------------------------: | ---- | |
|
|
|
| Towards Automatically-Tuned Deep Neural Networks | BOOK | [GitHub](https://github.com/automl/Auto-PyTorch) | | |
|
|
|
| [NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications](https://arxiv.org/pdf/1804.03230.pdf) | ECCV | [github](https://github.com/denru01/netadapt) | | |
|
|
|
| [Efficient Architecture Search by Network Transformation](https://arxiv.org/pdf/1707.04873.pdf) | AAAI | [github](https://github.com/han-cai/EAS) | | |
|
|
|
| [Learning Transferable Architectures for Scalable Image Recognition](http://openaccess.thecvf.com/content_cvpr_2018/papers/Zoph_Learning_Transferable_Architectures_CVPR_2018_paper.pdf) | CVPR | [github](https://github.com/tensorflow/models/tree/master/research/slim/nets/nasnet) | | |
|
|
|
| [N2N learning: Network to Network Compression via Policy Gradient Reinforcement Learning](https://openreview.net/forum?id=B1hcZZ-AW) | ICLR | - | | |
|
|
|
| [A Flexible Approach to Automated RNN Architecture Generation](https://openreview.net/forum?id=SkOb1Fl0Z) | ICLR | - | | |
|
|
|
| [Practical Block-wise Neural Network Architecture Generation](http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhong_Practical_Block-Wise_Neural_CVPR_2018_paper.pdf) | CVPR | - | | |
|
|
|
| [Path-Level Network Transformation for Efficient Architecture Search](https://arxiv.org/abs/1806.02639) | ICML | [github](https://github.com/han-cai/PathLevel-EAS) | | |
|
|
|
| [Hierarchical Representations for Efficient Architecture Search](https://openreview.net/forum?id=BJQRKzbA-) | ICLR | - | | |
|
|
|
| [Understanding and Simplifying One-Shot Architecture Search](http://proceedings.mlr.press/v80/bender18a/bender18a.pdf) | ICML | - | | |
|
|
|
| [SMASH: One-Shot Model Architecture Search through HyperNetworks](https://arxiv.org/pdf/1708.05344.pdf) | ICLR | [github](https://github.com/ajbrock/SMASH) | | |
|
|
|
| [Neural Architecture Optimization](https://arxiv.org/pdf/1808.07233.pdf) | NeurIPS | [github](https://github.com/renqianluo/NAO) | | |
|
|
|
| [Searching for efficient multi-scale architectures for dense image prediction](https://papers.nips.cc/paper/8087-searching-for-efficient-multi-scale-architectures-for-dense-image-prediction.pdf) | NeurIPS | - | | |
|
|
|
| [Progressive Neural Architecture Search](http://openaccess.thecvf.com/content_ECCV_2018/papers/Chenxi_Liu_Progressive_Neural_Architecture_ECCV_2018_paper.pdf) | ECCV | [github](https://github.com/chenxi116/PNASNet) | | |
|
|
|
| [Neural Architecture Search with Bayesian Optimisation and Optimal Transport](https://arxiv.org/pdf/1802.07191.pdf) | NeurIPS | [github](https://github.com/kirthevasank/nasbot) | | |
|
|
|
| [Differentiable Neural Network Architecture Search](https://openreview.net/pdf?id=BJ-MRKkwG) | ICLR-W | - | | |
|
|
|
| [Accelerating Neural Architecture Search using Performance Prediction](https://arxiv.org/abs/1705.10823) | ICLR-W | - | | |
|
|
|
|
|
|
|
### 2017 |
|
|
|
|
|
|
|
| Title | Venue | Code | Note | |
|
|
|
| :----------------------------------------------------------- | :-------: | :-----------------------------------------------: | ---- | |
|
|
|
| [Neural Architecture Search with Reinforcement Learning](https://arxiv.org/abs/1611.01578) | ICLR | - | | |
|
|
|
| [Designing Neural Network Architectures using Reinforcement Learning](https://openreview.net/pdf?id=S1c2cvqee) | ICLR | - | | |
|
|
|
| [Neural Optimizer Search with Reinforcement Learning](http://proceedings.mlr.press/v70/bello17a/bello17a.pdf) | ICML | - | | |
|
|
|
| [Learning Curve Prediction with Bayesian Neural Networks](http://ml.informatik.uni-freiburg.de/papers/17-ICLR-LCNet.pdf) | ICLR | - | | |
|
|
|
| [Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization](https://arxiv.org/abs/1603.06560) | ICLR | - | | |
|
|
|
| [Hyperparameter Optimization: A Spectral Approach](https://arxiv.org/abs/1706.00764) | NeurIPS-W | [github](https://github.com/callowbird/Harmonica) | | |
|
|
|
| Learning to Compose Domain-Specific Transformations for Data Augmentation | NeurIPS | - | | |
|
|
|
| Title | Venue | Code | Note | |
|
|
|
| :-------------------------------------------------------------------------------------------------------------------- | :-------: | :--------------------------------------------: | ---- | |
|
|
|
| [Neural Architecture Search with Reinforcement Learning](https://arxiv.org/abs/1611.01578) | ICLR | - | | |
|
|
|
| [Designing Neural Network Architectures using Reinforcement Learning](https://openreview.net/pdf?id=S1c2cvqee) | ICLR | - | | |
|
|
|
| [Neural Optimizer Search with Reinforcement Learning](http://proceedings.mlr.press/v70/bello17a/bello17a.pdf) | ICML | - | | |
|
|
|
| [Learning Curve Prediction with Bayesian Neural Networks](http://ml.informatik.uni-freiburg.de/papers/17-ICLR-LCNet.pdf) | ICLR | - | | |
|
|
|
| [Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization](https://arxiv.org/abs/1603.06560) | ICLR | - | | |
|
|
|
| [Hyperparameter Optimization: A Spectral Approach](https://arxiv.org/abs/1706.00764) | NeurIPS-W | [github](https://github.com/callowbird/Harmonica) | | |
|
|
|
| Learning to Compose Domain-Specific Transformations for Data Augmentation | NeurIPS | - | | |
|
|
|
|
|
|
|
### 2012-2016 |
|
|
|
|
|
|
|
| Title | Venue | Code | Note | |
|
|
|
| :----------------------------------------------------------- | :---: | :----------------------------------------------------------: | ---- | |
|
|
|
| Title | Venue | Code | Note | |
|
|
|
| :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :---: | :-------------------------------------------------------: | ---- | |
|
|
|
| [Speeding up Automatic Hyperparameter Optimization of Deep Neural Networksby Extrapolation of Learning Curves](http://ml.informatik.uni-freiburg.de/papers/15-IJCAI-Extrapolation_of_Learning_Curves.pdf) | IJCAI | [github](https://github.com/automl/pylearningcurvepredictor) | | |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
#### arXiv |
|
|
|
|
|
|
|
| Title | Date | Code | Note | |
|
|
|
| :----------------------------------------------------------- | :-----: | :----------------------------------------------------------: | ------------------------------------------------------------ | |
|
|
|
| [AutoHAS: Differentiable Hyper-parameter and Architecture Search](https://arxiv.org/pdf/2006.03656.pdf) | 2020.06 | - | | |
|
|
|
| [FBNetV3: Joint Architecture-Recipe Search using Neural Acquisition Function](https://arxiv.org/abs/2006.02049) | 2020.06 | [github](https://github.com/facebookresearch/mobile-vision/blob/main/mobile_cv/arch/fbnet_v2/fbnet_modeldef_cls_fbnetv3.py) | [NOTE](https://git.openi.org.cn/PCL_AutoML/AutoML/src/commit/62eed82bdd15b338ca09dfea26b5a8a77debd376/docs/notes/nas/FBNetV3_%20Joint%20Architecture-Recipe%20Search%20using%20Predictor%20Pretraining.pdf)| |
|
|
|
| [Population Based Training of Neural Networks](https://arxiv.org/abs/1711.09846) | 2017.11 | - | | |
|
|
|
| [NSGA-NET: A Multi-Objective Genetic Algorithm for Neural Architecture Search](https://arxiv.org/pdf/1810.03522.pdf) | 2018.10 | - | | |
|
|
|
| [Training Frankenstein’s Creature to Stack: HyperTree Architecture Search](https://arxiv.org/pdf/1810.11714.pdf) | 2018.10 | - | | |
|
|
|
| [Fast, Accurate and Lightweight Super-Resolution with Neural Architecture Search](https://arxiv.org/pdf/1901.07261.pdf) | 2019.01 | [github](https://github.com/falsr/FALSR) | | |
|
|
|
| Title | Date | Code | Note | |
|
|
|
| :------------------------------------------------------------------------------------------------------------------- | :-----: | :----------------------------------------------------------------------------------------------------------------------: | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | |
|
|
|
| [AutoHAS: Differentiable Hyper-parameter and Architecture Search](https://arxiv.org/pdf/2006.03656.pdf) | 2020.06 | - | | |
|
|
|
| [FBNetV3: Joint Architecture-Recipe Search using Neural Acquisition Function](https://arxiv.org/abs/2006.02049) | 2020.06 | [github](https://github.com/facebookresearch/mobile-vision/blob/main/mobile_cv/arch/fbnet_v2/fbnet_modeldef_cls_fbnetv3.py) | [NOTE](https://git.openi.org.cn/PCL_AutoML/AutoML/src/commit/62eed82bdd15b338ca09dfea26b5a8a77debd376/docs/notes/nas/FBNetV3_%20Joint%20Architecture-Recipe%20Search%20using%20Predictor%20Pretraining.pdf) | |
|
|
|
| [Population Based Training of Neural Networks](https://arxiv.org/abs/1711.09846) | 2017.11 | - | | |
|
|
|
| [NSGA-NET: A Multi-Objective Genetic Algorithm for Neural Architecture Search](https://arxiv.org/pdf/1810.03522.pdf) | 2018.10 | - | | |
|
|
|
| [Training Frankenstein’s Creature to Stack: HyperTree Architecture Search](https://arxiv.org/pdf/1810.11714.pdf) | 2018.10 | - | | |
|
|
|
| [Fast, Accurate and Lightweight Super-Resolution with Neural Architecture Search](https://arxiv.org/pdf/1901.07261.pdf) | 2019.01 | [github](https://github.com/falsr/FALSR) | | |
|
|
|
|
|
|
|
--- |
|
|
|
|
|
|
|
## Hyper Parameter Optimization |
|
|
|
|
|
|
|
| Title|Venue|Code| Note|Year| |
|
|
|
| :--- | :-----: | :------: | ----------- | ------- | |
|
|
|
| [BORE: Bayesian Optimization by Density-Ratio Estimation](http://proceedings.mlr.press/v139/tiao21a/tiao21a.pdf) |ICML |[GitHub](https://github.com/ltiao/bore)|[NOTE](https://git.openi.org.cn/PCL_AutoML/AutoML/src/commit/ab479b264106197958d7cfdf6be34f10ab5445e6/docs/notes/hpo/BORE_BayesianOptimization%20by_Density-Ratio_Estimation.pdf) |2021| |
|
|
|
| [Meta Learning Black-Box Population-Based Optimizers](https://arxiv.org/abs/2103.03526) |ArXiv |[GitHub](https://github.com/optimization-toolbox/meta-learning-population-based-optimizers) |[NOTE](https://git.openi.org.cn/PCL_AutoML/AutoML/src/commit/ab479b264106197958d7cfdf6be34f10ab5445e6/docs/notes/hpo/Meta%20Learning%20Black-Box%20Population-Based%20Optimizers.pdf)|2021| |
|
|
|
| [Transfer Bayesian Optimization](https://git.openi.org.cn/PCL_AutoML/AutoML/src/commit/ab479b264106197958d7cfdf6be34f10ab5445e6/docs/notes/hpo/Transfer_Bayesian_Optimization.pdf) | Note/Blog |[GitHub](https://git.openi.org.cn/PCL_AutoML/bbobenchmark) |[NOTE](https://git.openi.org.cn/PCL_AutoML/AutoML/src/commit/ab479b264106197958d7cfdf6be34f10ab5445e6/docs/notes/hpo/Transfer_Bayesian_Optimization.pdf)|2021| |
|
|
|
| [HEBO: Heteroscedastic Evolutionary Bayesian Optimisation](https://arxiv.org/pdf/2012.03826v1.pdf) |NeurIPS 2020 black-box competition |[GitHub](https://github.com/huawei-noah/noah-research/tree/master/BO/HEBO)|[NOTE](https://git.openi.org.cn/PCL_AutoML/AutoML/src/commit/ab479b264106197958d7cfdf6be34f10ab5445e6/docs/notes/hpo/HEBO_%20Heteroscedastic%20Evolutionary%20BayesianOptimisation.pdf) |2020| |
|
|
|
| [Learning Search Space Partition for Black-box Optimization using Monte Carlo Tree Search](http://arxiv.org/abs/2007.00708) |NeurIPS |[GitHub](https://github.com/facebookresearch/LaMCTS)|[NOTE](https://git.openi.org.cn/PCL_AutoML/AutoML/src/commit/ab479b264106197958d7cfdf6be34f10ab5445e6/docs/notes/hpo/Learning%20Search%20Space%20Partition%20for%20Black-box%20Optimization%20using%20Monte%20Carlo%20Tree%20Search.pdf) |2020| |
|
|
|
| [Scalable Global Optimization via Local Bayesian Optimization](http://papers.nips.cc/paper/8788-scalable-global-optimization-via-local-bayesian-optimization.pdf) |NeuriPS |[GitHub](https://github.com/uber-research/TuRBO) |[NOTE](https://git.openi.org.cn/PCL_AutoML/AutoML/src/commit/ab479b264106197958d7cfdf6be34f10ab5445e6/docs/notes/hpo/Scalable_Global_Optimization_via_Local_Bayesian_Optimization.pdf)|2019| |
|
|
|
| [Practical Transfer Learning for Bayesian Optimization](https://arxiv.org/abs/1802.02219) |ArXiv |- |[NOTE](https://git.openi.org.cn/PCL_AutoML/AutoML/src/commit/ab479b264106197958d7cfdf6be34f10ab5445e6/docs/notes/hpo/Practical_Transfer_Learning_for_Bayesian_Optimization.pdf)|2018| |
|
|
|
| [Two-stage transfer surrogate model for automatic hyperparameter optimization](http://arxiv.org/abs/1802.02219) |ECML |[GitHub](https://github.com/wistuba/TST) |[NOTE](https://git.openi.org.cn/PCL_AutoML/AutoML/src/commit/ab479b264106197958d7cfdf6be34f10ab5445e6/docs/notes/hpo/Two-stage_transfer_surrogate_model_for_automatic_hyperparameter_optimization.pdf)|2016| |
|
|
|
| Title | Venue | Code | Note | Year | |
|
|
|
| :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | :---------------------------------: | :--------------------------------------------------------------------------------------: | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---- | |
|
|
|
| [BORE: Bayesian Optimization by Density-Ratio Estimation](http://proceedings.mlr.press/v139/tiao21a/tiao21a.pdf) | ICML | [GitHub](https://github.com/ltiao/bore) | [NOTE](https://git.openi.org.cn/PCL_AutoML/AutoML/src/commit/ab479b264106197958d7cfdf6be34f10ab5445e6/docs/notes/hpo/BORE_BayesianOptimization%20by_Density-Ratio_Estimation.pdf) | 2021 | |
|
|
|
| [Meta Learning Black-Box Population-Based Optimizers](https://arxiv.org/abs/2103.03526) | ArXiv | [GitHub](https://github.com/optimization-toolbox/meta-learning-population-based-optimizers) | [NOTE](https://git.openi.org.cn/PCL_AutoML/AutoML/src/commit/ab479b264106197958d7cfdf6be34f10ab5445e6/docs/notes/hpo/Meta%20Learning%20Black-Box%20Population-Based%20Optimizers.pdf) | 2021 | |
|
|
|
| [Transfer Bayesian Optimization](https://git.openi.org.cn/PCL_AutoML/AutoML/src/commit/ab479b264106197958d7cfdf6be34f10ab5445e6/docs/notes/hpo/Transfer_Bayesian_Optimization.pdf) | Note/Blog | [GitHub](https://git.openi.org.cn/PCL_AutoML/bbobenchmark) | [NOTE](https://git.openi.org.cn/PCL_AutoML/AutoML/src/commit/ab479b264106197958d7cfdf6be34f10ab5445e6/docs/notes/hpo/Transfer_Bayesian_Optimization.pdf) | 2021 | |
|
|
|
| [HEBO: Heteroscedastic Evolutionary Bayesian Optimisation](https://arxiv.org/pdf/2012.03826v1.pdf) | NeurIPS 2020 black-box competition | [GitHub](https://github.com/huawei-noah/noah-research/tree/master/BO/HEBO) | [NOTE](https://git.openi.org.cn/PCL_AutoML/AutoML/src/commit/ab479b264106197958d7cfdf6be34f10ab5445e6/docs/notes/hpo/HEBO_%20Heteroscedastic%20Evolutionary%20BayesianOptimisation.pdf) | 2020 | |
|
|
|
| [Learning Search Space Partition for Black-box Optimization using Monte Carlo Tree Search](http://arxiv.org/abs/2007.00708) | NeurIPS | [GitHub](https://github.com/facebookresearch/LaMCTS) | [NOTE](https://git.openi.org.cn/PCL_AutoML/AutoML/src/commit/ab479b264106197958d7cfdf6be34f10ab5445e6/docs/notes/hpo/Learning%20Search%20Space%20Partition%20for%20Black-box%20Optimization%20using%20Monte%20Carlo%20Tree%20Search.pdf) | 2020 | |
|
|
|
| [Scalable Global Optimization via Local Bayesian Optimization](http://papers.nips.cc/paper/8788-scalable-global-optimization-via-local-bayesian-optimization.pdf) | NeuriPS | [GitHub](https://github.com/uber-research/TuRBO) | [NOTE](https://git.openi.org.cn/PCL_AutoML/AutoML/src/commit/ab479b264106197958d7cfdf6be34f10ab5445e6/docs/notes/hpo/Scalable_Global_Optimization_via_Local_Bayesian_Optimization.pdf) | 2019 | |
|
|
|
| [Practical Transfer Learning for Bayesian Optimization](https://arxiv.org/abs/1802.02219) | ArXiv | - | [NOTE](https://git.openi.org.cn/PCL_AutoML/AutoML/src/commit/ab479b264106197958d7cfdf6be34f10ab5445e6/docs/notes/hpo/Practical_Transfer_Learning_for_Bayesian_Optimization.pdf) | 2018 | |
|
|
|
| [Two-stage transfer surrogate model for automatic hyperparameter optimization](http://arxiv.org/abs/1802.02219) | ECML | [GitHub](https://github.com/wistuba/TST) | [NOTE](https://git.openi.org.cn/PCL_AutoML/AutoML/src/commit/ab479b264106197958d7cfdf6be34f10ab5445e6/docs/notes/hpo/Two-stage_transfer_surrogate_model_for_automatic_hyperparameter_optimization.pdf) | 2016 | |
|
|
|
|
|
|
|
--- |
|
|
|
## Automatic Network Compression |
|
|
|
|
|
|
|
## Automatic Network Compression |