Can Persistent Homology provide an efficient alternative for Evaluation of Knowledge Graph Completion Methods?
Can Persistent Homology provide an efficient alternative for Evaluation of Knowledge Graph Completion Methods?
复制标题
DOI：
10.1145/3543507.3583308
复制
发表时间：
2023-01
期刊：
影响因子：
--
通讯作者：
Anson Bastos;Kuldeep Singh;Abhishek Nadgeri;Johannes Hoffart;T. Suzumura;Manish Singh
中科院分区：
文献类型：
--
作者：
Anson Bastos;Kuldeep Singh;Abhishek Nadgeri;Johannes Hoffart;T. Suzumura;Manish Singh
在本文中，我们提出了一种新的方法，知识持久性（），以更快地评估知识图（KG）补全方法。当前基于排名的评估在KG的大小上是二次的，导致评估时间长，因此碳足迹高。通过拓扑数据分析来表示KG完井方法的拓扑，具体使用持久同构来解决这个问题。持续同源性的特点允许仅通过一小部分数据来评估KG完井的质量。在标准数据集上的实验结果表明，所提出的度量与排名度量（Hits@N， MR， MRR）高度相关。性能评估表明，该方法具有计算效率：在某些情况下，KG完成方法的评估时间（验证+测试）从18小时（使用Hits@10）减少到27秒（使用），平均而言（跨方法和数据）将评估时间（验证+测试）减少约99.96%。
In this paper we present a novel method, Knowledge Persistence (), for faster evaluation of Knowledge Graph (KG) completion approaches. Current ranking-based evaluation is quadratic in the size of the KG, leading to long evaluation times and consequently a high carbon footprint. addresses this by representing the topology of the KG completion methods through the lens of topological data analysis, concretely using persistent homology. The characteristics of persistent homology allow to evaluate the quality of the KG completion looking only at a fraction of the data. Experimental results on standard datasets show that the proposed metric is highly correlated with ranking metrics (Hits@N, MR, MRR). Performance evaluation shows that is computationally efficient: In some cases, the evaluation time (validation+test) of a KG completion method has been reduced from 18 hours (using Hits@10) to 27 seconds (using ), and on average (across methods & data) reduces the evaluation time (validation+test) by ≈ 99.96%.