VEM 2 L: An easy but effective framework for fusing text and structure knowledge on sparse knowledge graph completion

• المؤلفون الرئيسيون: HE, Tao, LIU, Ming, CAO, Yixin, QU, Meng, ZHENG, Zihao, QIN, Bing
• التنسيق: text
• اللغة: English
• منشور في: Institutional Knowledge at Singapore Management University 2024
• الموضوعات: Centralized optimization; data-driven optimization; distributed optimization; evolutionary computation; privacy protection; Databases and Information Systems
• الوصول للمادة أونلاين: https://ink.library.smu.edu.sg/sis_research/8664
• المؤسسة: Singapore Management University

The task of Knowledge Graph Completion (KGC) is to infer missing links for Knowledge Graphs (KGs) by analyzing graph structures. However, with increasing sparsity in KGs, this task becomes increasingly challenging. In this paper, we propose VEM2L, a joint learning framework that incorporates structu...