为PyKEEN添加多种负采样方法，提升知识图谱嵌入性能
Enhancing PyKEEN with Multiple Negative Sampling Solutions for Knowledge Graph Embedding Models
- 集成静态与动态负采样策略，统一模块化架构
- 实测多模型在链接预测任务上性能显著提升
- 适合研究者快速定制和评估嵌入方法
嵌入方法因其在知识图谱的链接预测和/或三元组分类任务上的可扩展性而广受欢迎。嵌入模型训练依赖正例与负例三元组。然而，在缺乏负命题的情况下，通常需通过各种负采样策略人工生成负例，从随机破坏到更复杂的技巧，这些策略对整体性能有显著影响。目前大多数流行的知识图谱嵌入库仅支持基础采样策略，缺乏高级解决方案。为此，本文为流行的KGE框架PyKEEN开发了一个扩展，集成了多种先进负采样器（包括静态与动态破坏策略），在一致的模块化架构中生成有意义的负样本，同时保持与现有PyKEEN工作流和管道的兼容性。该扩展不仅增强了PyKEEN本身，还便于嵌入方法的开发与定制。作为概念验证，我们进行了全面的实证研究，评估所提扩展对不同嵌入方法性能（链接预测任务）的影响，也为设计更有效的策略提供了有益见解。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。