| 引用本文: | 童翰文,钱羽希,刘井平,梁祖杰,肖仰华,韦峰,郝正鸿,韩冰.带有差异化机制的多视角归纳式知识图谱补全框架.软件学报,2025,36(12):5629-5643 |
| |
|
| |
|
|
| 本文已被：浏览 786次 下载 1311次 |
码上扫一扫！ |
|
|
| 带有差异化机制的多视角归纳式知识图谱补全框架 |
|
童翰文1,2, 钱羽希3, 刘井平4, 梁祖杰3, 肖仰华1,2, 韦峰3, 郝正鸿3, 韩冰3
|
|
1.复旦大学 计算机科学技术学院, 上海 200438;2.上海市数据科学重点实验室(复旦大学), 上海 200438;3.蚂蚁集团, 上海 200010;4.华东理工大学 信息科学与工程学院, 上海 200237
|
|
| 摘要: |
| 知识图谱补全模型需要具备归纳能力, 才能够随着知识图谱的扩充泛化到新实体上. 然而, 现有的方法都只能通过聚合知识图谱中的邻居信息, 从一个局部的视角来理解实体的语义, 从而导致无法从不同的视角捕捉到实体之间的多种有价值的关联. 在局部视角以外, 通过非显式连接实体之间和远距离连接实体之间的交互, 从而以全局视角和序列视角来进一步理解实体是至关重要的. 更重要的是, 强调通过多个不同视角聚合到的信息应当是互补的, 而不是冗余的. 因此, 提出一个带有差异化机制的多视角知识图谱补全框架, 用于归纳式知识图谱补全任务. 它能够从多个不同视角学习到互补的、互不重叠的实体表示. 具体来说, 除了通过关系图卷积网络聚合邻居信息得到实体的局部表示外, 设计一种基于注意力的差异化机制, 用于从语义相关的实体和实体相关路径中聚合得到实体的全局和序列表示. 最终, 融合这些表示, 并基于它们给三元组打分. 实验结果证明, 所提方法在归纳式的设定下超越了当前最先进的方法. 此外, 所提方法在直推式的知识图谱补全任务中也保持着有竞争力的表现. |
| 关键词: 归纳式知识图谱补全 多视角框架 差异化机制 知识图谱 |
| DOI：10.13328/j.cnki.jos.007401 |
| 分类号:TP182 |
| 基金项目:国家自然科学基金青年科学基金 (62306112); 上海市青年科技英才扬帆计划 (23YF1409400); 上海市基础研究特区计划 (22TQ1400100-20) |
|
| Multi-view Framework for Inductive Knowledge Graph Completion with Differentiation Mechanism |
|
TONG Han-Wen1,2, QIAN Yu-Xi3, LIU Jing-Ping4, LIANG Zu-Jie3, XIAO Yang-Hua1,2, WEI Feng3, HAO Zheng-Hong3, HAN Bing3
|
|
1.School of Computer Science, Fudan University, Shanghai 200438, China;2.Shanghai Key Laboratory of Data Science (Fudan University), Shanghai 200438, China;3.Ant Group, Shanghai 200010, China;4.School of Information Science and Engineering, East China University of Science and Technology, Shanghai 200237, China
|
| Abstract: |
| Knowledge graph completion (KGC) models require inductive ability to generalize to new entities as the knowledge graph expands. However, current approaches understand entities only from a local perspective by aggregating neighboring information, failing to capture valuable interconnections between entities across different views. This study argues that global and sequential perspectives are essential for understanding entities beyond the local view by enabling interaction between disconnected and distant entity pairs. More importantly, it emphasizes that the aggregated information must be complementary across different views to avoid redundancy. Therefore, a multi-view framework with the differentiation mechanism is proposed for inductive KGC, aimed at learning complementary entity representations from various perspectives. Specifically, in addition to aggregating neighboring information to obtain the entity’s local representation through R-GCN, an attention-based differentiation mechanism is employed to aggregate complementary information from semantically related entities and entity-related paths, thus obtaining global and sequential representations of the entities. Finally, these representations are fused and used to score the triples. Experimental results demonstrate that the proposed framework consistently outperforms state-of-the-art approaches in the inductive setting. Moreover, it retains competitive performance in the transductive setting. |
| Key words: inductive knowledge graph completion multi-view framework differentiation mechanism knowledge graph |
|
|
|
|
