PyKEEN 1.0: A Python Library for Training and Evaluating Knowledge Graph Embeddings
arXiv:2007.14175
Abstract
Recently, knowledge graph embeddings (KGEs) received significant attention, and several software libraries have been developed for training and evaluating KGEs. While each of them addresses specific needs, we re-designed and re-implemented PyKEEN, one of the first KGE libraries, in a community effort. PyKEEN 1.0 enables users to compose knowledge graph embedding models (KGEMs) based on a wide range of interaction models, training approaches, loss functions, and permits the explicit modeling of inverse relations. Besides, an automatic memory optimization has been realized in order to exploit the provided hardware optimally, and through the integration of Optuna extensive hyper-parameter optimization (HPO) functionalities are provided.
References in corpus (6)
- Scikit-learn: Machine Learning in Python
- A Review of Relational Machine Learning for Knowledge Graphs
- Bringing Light Into the Dark: A Large-scale Evaluation of Knowledge Graph Embedding Models Under a Unified Framework
- GraphVite: A High-Performance CPU-GPU Hybrid System for Node Embedding
- DGL-KE: Training Knowledge Graph Embeddings at Scale
- Pykg2vec: A Python Library for Knowledge Graph Embedding
Cited by in corpus (4)
- Understanding the Performance of Knowledge Graph Embeddings in Drug Discovery
- Triple Classification for Scholarly Knowledge Graph Completion
- Unified Interpretation of Softmax Cross-Entropy and Negative Sampling: With Case Study for Knowledge Graph Embedding
- Knowledge Sheaves: A Sheaf-Theoretic Framework for Knowledge Graph Embedding