PyKEEN 1.0: A Python Library for Training and Evaluating Knowledge Graph Embeddings
This provides a comprehensive tool for researchers and practitioners working with knowledge graph embeddings, though it is incremental as a library update.
The authors redesigned PyKEEN, a Python library for knowledge graph embeddings, to enable flexible composition of models, training approaches, and loss functions, while adding features like automatic memory optimization and hyper-parameter optimization.
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.