Enhancing PyKEEN with Multiple Negative Sampling Solutions for Knowledge Graph Embedding Models

TL;DR

This paper introduces an extension to PyKEEN that incorporates multiple advanced negative sampling strategies, improving the quality of negative samples and enhancing the performance of knowledge graph embedding models.

Contribution

The paper presents a modular extension for PyKEEN supporting various negative sampling methods, facilitating better embedding training and customization.

Findings

Advanced negative samplers improve link prediction accuracy.

The extension is compatible with existing workflows and enhances model development.

Empirical results demonstrate the effectiveness of the new sampling strategies.

Abstract

Embedding methods have become popular due to their scalability on link prediction and/or triple classification tasks on Knowledge Graphs. Embedding models are trained relying on both positive and negative samples of triples. However, in the absence of negative assertions, these must be usually artificially generated using various negative sampling strategies, ranging from random corruption to more sophisticated techniques which have an impact on the overall performance. Most of the popular libraries for knowledge graph embedding, support only basic such strategies and lack advanced solutions. To address this gap, we deliver an extension for the popular KGE framework PyKEEN that integrates a suite of several advanced negative samplers (including both static and dynamic corruption strategies), within a consistent modular architecture, to generate meaningful negative samples, while remaining compatible with existing PyKEEN -based workflows and pipelines. The developed extension not only enhancesPyKEEN itself but also allows for easier and comprehensive development of embedding methods and/or for their customization. As a proof of concept, we present a comprehensive empirical study of the developed extensions and their impact on the performance (link prediction tasks) of different embedding methods, which also provides useful insights for the design of more effective strategies