pykeen

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
Inductive Link Prediction
Splitting
PyTorch Lightning Integration
Using Resolvers
Normalizer, Constrainer & Regularizer
Troubleshooting

Bring Your Own

Bring Your Own Data
Bring Your Own Interaction

Extending PyKEEN

Extending the Datasets
Extending the Models

Reference

Pipeline
- Functions
- Classes
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
Flexible Weight Checkpoints
pykeen.nn
Utilities

Appendix

Analysis
References

pykeen

Pipeline
plot_losses
View page source

plot_losses

plot_losses(pipeline_result, *, ax=None)[source]: Plot the losses per epoch.

Previous Next

© Copyright 2019-2025, PyKEEN Project Team.

Built with Sphinx using a theme provided by Read the Docs.