当成功的知识图谱编辑取代正确答案：参数支持之外的排名级局部性

中文摘要 AI 辅助

编辑知识图谱嵌入（KGE）模型以提升期望答案，可能会将正确答案从返回列表中挤出。仅基于重用被编辑参数的事实的局部性测试，可能会遗漏这种排名效应。我们在三个范围内引入了一种常见的排名位移审计：由被编辑参数支持的事实、目标查询的其他正确答案，以及具有相同关系的查询中的正确答案。我们还推导了更新的维度和几何条件，使更新在精确保留选定分数的同时提升目标。在FB15k-237上使用DistMult和ComplEx，直接提升总是将目标移入前十，但仅在23.0%至23.2%的编辑中无损害地做到这一点。严格保留不会造成可测量的损害，但成功率仅为1.3%至1.4%。支持正则化的实体编辑给出了最高的联合成功率，为36.3%至37.7%，而排名截断保留达到32.8%至34.7%，并将被位移答案的平均数量从约14个减少到1.2个。跨维度、评分器、排名约定和学习的编辑器的实验表明，局部性既取决于受保护的范围，也取决于编辑机制。因此，KGE编辑应同时报告修正成功率以及排名位移的发生率和严重程度。

英文摘要

Editing a knowledge graph embedding (KGE) model to promote a desired answer can displace correct answers from the returned list. Locality tests based only on facts that reuse the edited parameter can miss this ranking effect. We introduce a common rank-displacement audit at three scopes: facts supported by the edited parameter, other correct answers to the target query, and correct answers across queries with the same relation. We also derive dimensional and geometric conditions for an update to improve the target while exactly preserving selected scores. On FB15k-237 with DistMult and ComplEx, direct promotion always moves the target into the top ten, but does so without damage in only 23.0--23.2\% of edits. Strict preservation causes no measured damage, yet succeeds in only 1.3--1.4\%. Support-regularized entity editing gives the highest joint success, 36.3--37.7\%, while rank-truncated preservation reaches 32.8--34.7\% and reduces the mean number of displaced answers from about 14 to 1.2. Experiments across dimensions, scorers, ranking conventions, and a learned editor show that locality depends on both the protected scope and the editing mechanism. KGE editing should therefore report correction success together with the incidence and severity of rank displacement.

发表机构

• Institute of Information Science, Academia Sinica（中央研究院资讯科学研究所）
• University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
• National Chengchi University（国立政治大学）

机构由 AI 辅助整理，请以论文原文为准。