Lookup

models: Mapping[str, Type[pykeen.models.base.Model]] = {'complex': <class 'pykeen.models.unimodal.complex.ComplEx'>, 'complexliteral': <class 'pykeen.models.multimodal.complex_literal.ComplExLiteral'>, 'conve': <class 'pykeen.models.unimodal.conv_e.ConvE'>, 'convkb': <class 'pykeen.models.unimodal.conv_kb.ConvKB'>, 'distmult': <class 'pykeen.models.unimodal.distmult.DistMult'>, 'distmultliteral': <class 'pykeen.models.multimodal.distmult_literal.DistMultLiteral'>, 'ermlp': <class 'pykeen.models.unimodal.ermlp.ERMLP'>, 'ermlpe': <class 'pykeen.models.unimodal.ermlpe.ERMLPE'>, 'hole': <class 'pykeen.models.unimodal.hole.HolE'>, 'kg2e': <class 'pykeen.models.unimodal.kg2e.KG2E'>, 'ntn': <class 'pykeen.models.unimodal.ntn.NTN'>, 'proje': <class 'pykeen.models.unimodal.proj_e.ProjE'>, 'rescal': <class 'pykeen.models.unimodal.rescal.RESCAL'>, 'rgcn': <class 'pykeen.models.unimodal.rgcn.RGCN'>, 'rotate': <class 'pykeen.models.unimodal.rotate.RotatE'>, 'simple': <class 'pykeen.models.unimodal.simple.SimplE'>, 'structuredembedding': <class 'pykeen.models.unimodal.structured_embedding.StructuredEmbedding'>, 'transd': <class 'pykeen.models.unimodal.trans_d.TransD'>, 'transe': <class 'pykeen.models.unimodal.trans_e.TransE'>, 'transh': <class 'pykeen.models.unimodal.trans_h.TransH'>, 'transr': <class 'pykeen.models.unimodal.trans_r.TransR'>, 'tucker': <class 'pykeen.models.unimodal.tucker.TuckER'>, 'unstructuredmodel': <class 'pykeen.models.unimodal.unstructured_model.UnstructuredModel'>}

A mapping of models’ names to their implementations

losses: Mapping[str, Type[pykeen.losses.Loss]] = {'bceaftersigmoid': <class 'pykeen.losses.BCEAfterSigmoidLoss'>, 'bcewithlogits': <class 'pykeen.losses.BCEWithLogitsLoss'>, 'crossentropy': <class 'pykeen.losses.CrossEntropyLoss'>, 'marginranking': <class 'pykeen.losses.MarginRankingLoss'>, 'mse': <class 'pykeen.losses.MSELoss'>, 'nssa': <class 'pykeen.losses.NSSALoss'>, 'softplus': <class 'pykeen.losses.SoftplusLoss'>}

A mapping of losses’ names to their implementations

optimizers: Mapping[str, Type[torch.optim.optimizer.Optimizer]] = {'adadelta': <class 'torch.optim.adadelta.Adadelta'>, 'adagrad': <class 'torch.optim.adagrad.Adagrad'>, 'adam': <class 'torch.optim.adam.Adam'>, 'adamax': <class 'torch.optim.adamax.Adamax'>, 'adamw': <class 'torch.optim.adamw.AdamW'>, 'sgd': <class 'torch.optim.sgd.SGD'>}

A mapping of optimizers’ names to their implementations

regularizers: Mapping[str, Type[pykeen.regularizers.Regularizer]] = {'combined': <class 'pykeen.regularizers.CombinedRegularizer'>, 'lp': <class 'pykeen.regularizers.LpRegularizer'>, 'no': <class 'pykeen.regularizers.NoRegularizer'>, 'powersum': <class 'pykeen.regularizers.PowerSumRegularizer'>, 'transh': <class 'pykeen.regularizers.TransHRegularizer'>}

A mapping of regularizers’ names to their implementations

stoppers: Mapping[str, Type[pykeen.stoppers.stopper.Stopper]] = {'early': <class 'pykeen.stoppers.early_stopping.EarlyStopper'>, 'nop': <class 'pykeen.stoppers.stopper.NopStopper'>}

A mapping of stoppers’ names to their implementations

negative_samplers: Mapping[str, Type[pykeen.sampling.negative_sampler.NegativeSampler]] = {'basic': <class 'pykeen.sampling.basic_negative_sampler.BasicNegativeSampler'>, 'bernoulli': <class 'pykeen.sampling.bernoulli_negative_sampler.BernoulliNegativeSampler'>}

A mapping of negative samplers’ names to their implementations

datasets: Mapping[str, Type[pykeen.datasets.base.Dataset]] = {'ckg': <class 'pykeen.datasets.ckg.CKG'>, 'codexlarge': <class 'pykeen.datasets.codex.CoDExLarge'>, 'codexmedium': <class 'pykeen.datasets.codex.CoDExMedium'>, 'codexsmall': <class 'pykeen.datasets.codex.CoDExSmall'>, 'conceptnet': <class 'pykeen.datasets.conceptnet.ConceptNet'>, 'drkg': <class 'pykeen.datasets.drkg.DRKG'>, 'fb15k': <class 'pykeen.datasets.freebase.FB15k'>, 'fb15k237': <class 'pykeen.datasets.freebase.FB15k237'>, 'hetionet': <class 'pykeen.datasets.hetionet.Hetionet'>, 'kinships': <class 'pykeen.datasets.kinships.Kinships'>, 'nations': <class 'pykeen.datasets.nations.Nations'>, 'ogbbiokg': <class 'pykeen.datasets.ogb.OGBBioKG'>, 'ogbwikikg': <class 'pykeen.datasets.ogb.OGBWikiKG'>, 'openbiolink': <class 'pykeen.datasets.openbiolink.OpenBioLink'>, 'openbiolinkf1': <class 'pykeen.datasets.openbiolink.OpenBioLinkF1'>, 'openbiolinkf2': <class 'pykeen.datasets.openbiolink.OpenBioLinkF2'>, 'openbiolinklq': <class 'pykeen.datasets.openbiolink.OpenBioLinkLQ'>, 'umls': <class 'pykeen.datasets.umls.UMLS'>, 'wn18': <class 'pykeen.datasets.wordnet.WN18'>, 'wn18rr': <class 'pykeen.datasets.wordnet.WN18RR'>, 'yago310': <class 'pykeen.datasets.yago.YAGO310'>}

A mapping of datasets’ names to their classes

training_loops: Mapping[str, Type[pykeen.training.training_loop.TrainingLoop]] = {'lcwa': <class 'pykeen.training.lcwa.LCWATrainingLoop'>, 'slcwa': <class 'pykeen.training.slcwa.SLCWATrainingLoop'>}

A mapping of training loops’ names to their implementations

evaluators: Mapping[str, Type[pykeen.evaluation.evaluator.Evaluator]] = {'rankbased': <class 'pykeen.evaluation.rank_based_evaluator.RankBasedEvaluator'>, 'sklearn': <class 'pykeen.evaluation.sklearn.SklearnEvaluator'>}

A mapping of evaluators’ names to their implementations

metrics: Mapping[str, Type[pykeen.evaluation.evaluator.MetricResults]] = {'rankbased': <class 'pykeen.evaluation.rank_based_evaluator.RankBasedMetricResults'>, 'sklearn': <class 'pykeen.evaluation.sklearn.SklearnMetricResults'>}

A mapping of results’ names to their implementations

pruners: Mapping[str, Type[optuna.pruners._base.BasePruner]] = {'median': <class 'optuna.pruners._median.MedianPruner'>, 'nop': <class 'optuna.pruners._nop.NopPruner'>, 'percentile': <class 'optuna.pruners._percentile.PercentilePruner'>, 'successivehalving': <class 'optuna.pruners._successive_halving.SuccessiveHalvingPruner'>}

A mapping of HPO pruners’ names to their implementations

samplers: Mapping[str, Type[optuna.samplers._base.BaseSampler]] = {'grid': <class 'optuna.samplers._grid.GridSampler'>, 'random': <class 'optuna.samplers._random.RandomSampler'>, 'tpe': <class 'optuna.samplers._tpe.sampler.TPESampler'>}

A mapping of HPO samplers’ names to their implementations