PyKEEN
PyKEEN is a Python package for reproducible, facile knowledge graph embeddings.
The fastest way to get up and running is to use the pykeen.pipeline.pipeline()
function.
It provides a high-level entry into the extensible functionality of
this package. The following example shows how to train and evaluate the
TransE model (pykeen.models.TransE) on the Nations dataset (pykeen.datasets.Nations)
by referring to them by name. By default, the training loop uses the stochastic closed world assumption training
approach
(pykeen.training.SLCWATrainingLoop) and evaluates with rank-based evaluation
(pykeen.evaluation.RankBasedEvaluator).
>>> from pykeen.pipeline import pipeline
>>> result = pipeline(
... model='TransE',
... dataset='Nations',
... )
The results are returned in a pykeen.pipeline.PipelineResult instance, which has
attributes for the trained model, the training loop, and the evaluation.
PyKEEN has a function pykeen.env() that magically prints relevant version information
about PyTorch, CUDA, and your operating system that can be used for debugging.
If you’re in a Jupyter notebook, it will be pretty printed as an HTML table.
>>> import pykeen
>>> pykeen.env()
Getting Started
- Installation
- First Steps
- Knowledge Graph Embedding Models
- Representations
- Tracking Results during Training
- Saving Checkpoints during Training
- A Toy Example with Translational Distance Models
- Understanding the Evaluation
- Optimizing a Model’s Hyper-parameters
- Running an Ablation Study
- Performance Tricks
- Getting Started with NodePiece
- Basic Usage
- Anchor Selection and Searching
- How many total anchors num_anchors and anchors & relations num_tokens do I need for my graph?
- Using NodePiece with
pykeen.pipeline.pipeline() - Pre-Computed Vocabularies
- Configuring the Interaction Function
- Configuring the Aggregation Function
- NodePiece + GNN
- Tokenizing Large Graphs with METIS
- Inductive Link Prediction
- Splitting
- PyTorch Lightning Integration
- Using Resolvers
- Normalizer, Constrainer & Regularizer
- Troubleshooting
Bring Your Own
- Bring Your Own Data
- Bring Your Own Interaction
- Implementing your first Interaction Module
- Interactions with Hyper-Parameters
- Interactions with Trainable Parameters
- Interactions with Different Shaped Vectors
- Interactions with Multiple Representations
- Interactions with Different Dimension Vectors
- Differences between
pykeen.nn.modules.Interactionandpykeen.models.Model - Ad hoc Models from Interactions
- Interaction Pipeline
Extending PyKEEN
Reference
- Pipeline
- Models
- Datasets
- Inductive Datasets
- Entity Alignment
- Triples
- Triples Workflows
- Training
- Stoppers
- Loss Functions
- Regularizers
- Result Trackers
- Negative Sampling
- Filtering
- Optimizers
- Evaluation
- Metrics
- Hyper-parameter Optimization
- Ablation
- Prediction
- Uncertainty
- Sealant
- Constants
PYKEEN_BENCHMARKSPYKEEN_CHECKPOINTSPYKEEN_DATASETSPYKEEN_EXPERIMENTSPYKEEN_HOMEPYKEEN_LOGSConstrainerDeviceHintGaussianDistributionHeadRepresentationInductiveModeInitializerLabeledTriplesMutationNormalizerRelationRepresentationTailRepresentationTargetTargetColumnTorchRandomHintcast_constrainer()normalize_rank_type()normalize_target()
- Flexible Weight Checkpoints
pykeen.nn- Utilities
BiasExtraReprMixinNoRandomSeedNecessaryResultall_in_bounds()at_least_eps()batched_dot()broadcast_upgrade_to_sequences()calculate_broadcasted_elementwise_result_shape()check_shapes()clamp_norm()combine_complex()compact_mapping()complex_normalize()composecreate_relation_to_entity_set_mapping()einsum()ensure_complex()ensure_ftp_directory()ensure_torch_random_state()ensure_tuple()estimate_cost_of_sequence()extend_batch()fix_dataclass_init_docs()flatten_dictionary()format_relative_comparison()get_batchnorm_modules()get_benchmark()get_connected_components()get_devices()get_df_io()get_dropout_modules()get_edge_index()get_expected_norm()get_json_bytes_io()get_model_io()get_optimal_sequence()get_preferred_device()get_until_first_blank()invert_mapping()is_triple_tensor_subset()isin_many_dim()logcumsumexp()lp_norm()negative_norm()negative_norm_of_sum()nested_get()normalize_path()normalize_string()powersum_norm()prepare_filter_triples()project_entity()random_non_negative_int()rate_limited()resolve_device()set_random_seed()split_complex()split_workload()tensor_product()tensor_sum()triple_tensor_to_set()unpack_singletons()upgrade_to_sequence()view_complex()env()get_git_branch()get_git_hash()get_version()