Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
Theheavens 9b56966ca5 | 2 years ago | |
---|---|---|
.. | ||
README.md | 2 years ago | |
__init__.py | 2 years ago | |
hpo.py | 2 years ago | |
hpo_space.py | 2 years ago |
We use a lightweight HPO framework Optuna where we can enjoy high modularity.
Just with a few lines of codes, we can define the whole experiment.
For now, we just need define the search func in func_search(trial). How to define, refer to Pythonic Search Space.
Optuna enables efficient hyperparameter optimization by adopting state-of-the-art algorithms for sampling hyperparameters and pruning efficiently unpromising trials.
We can use these optimization algorithms through passing the parameter when we define optuna.create_study.
Optuna provides the following sampling algorithms:
optuna.samplers.TPESampler
optuna.samplers.CmaEsSampler
optuna.samplers.GridSampler
optuna.samplers.RandomSampler
The default sampler is optuna.samplers.TPESampler
.
Pruners
automatically stop unpromising trials at the early stages of the training (a.k.a., automated early-stopping).
Optuna provides the following pruning algorithms:
optuna.pruners.SuccessiveHalvingPruner
optuna.pruners.HyperbandPruner
optuna.pruners.MedianPruner
optuna.pruners.ThresholdPruner
We use optuna.pruners.MedianPruner
in most examples, though basically it is outperformed by optuna.pruners.SuccessiveHalvingPruner
and optuna.pruners.HyperbandPruner
as in this benchmark result.
This is an open-source toolkit for Heterogeneous Graph Neural Network(OpenHGNN) based on DGL.
Python Markdown Shell other
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》