构建知识图谱链接预测解释的标准化评测工具库
GRainsaCK: a Comprehensive Software Library for Benchmarking Explanations of Link Prediction Tasks on Knowledge Graphs
- 提供统一评测流程，涵盖模型训练到解释评估全流程
- 支持可复现的定量比较，解决解释方法无标准评估难题
- 模块化设计易扩展，适合研究者快速搭建评测框架
由于知识图谱通常不完整，链路预测方法被用于推断缺失事实。目前主流采用可扩展的嵌入方法，但缺乏可解释性，这在某些领域至关重要。解释方法通过识别支持性知识来说明预测结果。然而，量化评估或比较解释效果困难，因缺乏标准评估协议和统一基准资源。本文提出 GRainsaCK，一个可复用的软件库，全面简化解释评测全过程，从模型训练到解释评估均遵循一致协议。此外，该库通过函数化设计实现高模块化与可扩展性，主要组件可轻松替换。为促进复用，我们还提供了详尽文档和教程。
原文摘要 · Abstract (English)
Since Knowledge Graphs are often incomplete, link prediction methods are adopted for predicting missing facts. Scalable embedding based solutions are mostly adopted for this purpose, however, they lack comprehensibility, which may be crucial in several domains. Explanation methods tackle this issue by identifying supporting knowledge explaining the predicted facts. Regretfully, evaluating/comparing quantitatively the resulting explanations is challenging as there is no standard evaluation protocol and overall benchmarking resource. We fill this important gap by proposing GRainsaCK, a reusable software resource that fully streamlines all the tasks involved in benchmarking explanations, i.e., from model training to evaluation of explanations along the same evaluation protocol. Moreover, GRainsaCK furthers modularity/extensibility by implementing the main components as functions that can be easily replaced. Finally, fostering its reuse, we provide extensive documentation including a tutorial.
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。