提出新模型解决知识图谱对齐中跨图泛化难题
Breaking the Reasoning Horizon in Entity Alignment Foundation Models
- 用种子对齐对作为局部锚点，双路并行编码增强信息传递
- 在多个未见过的知识图谱上实现90%以上准确率，显著优于基线
- 适合需要跨域对齐的场景，如异构数据融合与开放世界知识集成
实体对齐（EA）对知识图谱融合至关重要。现有模型缺乏迁移能力，无法在不重新训练的情况下对未见知识图谱进行对齐。尽管图基础模型（GFMs）提供了潜在解决方案，但直接适配仍效果不佳，根源在于‘推理视野差距’：不同于图模型中的链接预测，实体对齐需捕捉稀疏且异构结构中的长程依赖。为此，我们提出一种基于并行编码策略的实体对齐基础模型。利用已知的种子对齐对作为局部锚点，同时初始化并编码两条并行流，实现锚点引导的消息传递，显著缩短推理路径，通过局部结构邻近性替代全局搜索。此外，引入合并关系图建模全局依赖，并设计可学习交互模块实现精确匹配。大量实验验证了该框架的有效性，其在未见知识图谱上展现出强泛化能力。
原文摘要 · Abstract (English)
Entity alignment (EA) is critical for knowledge graph (KG) fusion. Existing EA models lack transferability and are incapable of aligning unseen KGs without retraining. While using graph foundation models (GFMs) offer a solution, we find that directly adapting GFMs to EA remains largely ineffective. This stems from a critical "reasoning horizon gap": unlike link prediction in GFMs, EA necessitates capturing long-range dependencies across sparse and heterogeneous KG structuresTo address this challenge, we propose a EA foundation model driven by a parallel encoding strategy. We utilize seed EA pairs as local anchors to guide the information flow, initializing and encoding two parallel streams simultaneously. This facilitates anchor-conditioned message passing and significantly shortens the inference trajectory by leveraging local structural proximity instead of global search. Additionally, we incorporate a merged relation graph to model global dependencies and a learnable interaction module for precise matching. Extensive experiments verify the effectiveness of our framework, highlighting its strong generalizability to unseen KGs.
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。