autogllight.hpo

class autogllight.hpo.AnnealAdvisorHPO(*args, **kwargs)[source]: Simulate anneal algorithm in advisor package See https://github.com/tobegit3hub/advisor for the package See .advisorbase.AdvisorBaseHPOptimizer for more information

class autogllight.hpo.AutoNE(*args, **kwargs)[source]

AutoNE HPOptimizer The Implementation of “AutoNE: Hyperparameter Optimization for Massive Network Embedding”(KDD 2019). See https://github.com/tadpole/AutoNE for more information

max_evals

The max rounds of evaluating HPs

Type:: int

subgraphs

The number of subgraphs

Type:: int

sub_evals

The number of evaluation times on each subgraph

Type:: int

sample_batch_size, sample_walk_length

Using for sampling subgraph, see torch_geometric.data.GraphSAINRandomWalkSampler

Type:: int

optimize()[source]

Optimize the HP by the method within give model and HP space

See .base.BaseHPOptimizer.optimize

class autogllight.hpo.BayesAdvisor(*args, **kwargs)[source]: Bayes algorithm in advisor package See https://github.com/tobegit3hub/advisor for the package See .advisorbase.AdvisorBaseHPOptimizer for more information

class autogllight.hpo.CmaesAdvisorChoco(*args, **kwargs)[source]: CMAES algorithm in advisor package See https://github.com/tobegit3hub/advisor for the package See .advisorbase.AdvisorBaseHPOptimizer for more information

class autogllight.hpo.GridAdvisor(*args, **kwargs)[source]: Grid search algorithm in advisor package See https://github.com/tobegit3hub/advisor for the package See .advisorbase.AdvisorBaseHPOptimizer for more information

class autogllight.hpo.MocmaesAdvisorChoco(args)[source]: MOCMAES algorithm in advisor package See https://github.com/tobegit3hub/advisor for the package See .advisorbase.AdvisorBaseHPOptimizer for more information

class autogllight.hpo.QuasiAdvisorChoco(*args, **kwargs)[source]: Quasi random search algorithm in advisor package See https://github.com/tobegit3hub/advisor for the package See .advisorbase.AdvisorBaseHPOptimizer for more information

class autogllight.hpo.RandAdvisor(*args, **kwargs)[source]: Random search algorithm in advisor package See https://github.com/tobegit3hub/advisor for the package See .advisorbase.AdvisorBaseHPOptimizer for more information

class autogllight.hpo.TpeAdvisorHPO(*args, **kwargs)[source]: TPE algorithm in advisor package See https://github.com/tobegit3hub/advisor for the package See .advisorbase.AdvisorBaseHPOptimizer for more information

autogllight.hpo.build_hpo_from_name(name: str, *args, **kwargs) → BaseHPOptimizer[source]

Parameters:: name (str) – the name of hpo module.
Returns:: the HPO built using default parameters
Return type:: BaseHPOptimizer
Raises:: AssertionError – If an invalid name is passed in