The objective of Entity Alignment (EA) is to identify equivalent entity pairs from multiple Knowledge Graphs (KGs) and create a more comprehensive and unified KG. The majority of EA methods have primarily focused on the structural modality of KGs, lacking exploration of multi-modal information. A few multi-modal EA methods have made good attempts in this field. Still, they have two shortcomings: (1) inconsistent and inefficient modality modeling that designs complex and distinct models for each modality; (2) ineffective modality fusion due to the heterogeneous nature of modalities in EA. To tackle these challenges, we propose PathFusion, consisting of two main components: (1) MSP, a unified modeling approach that simplifies the alignment process by constructing paths connecting entities and modality nodes to represent multiple modalities; (2) IRF, an iterative fusion method that effectively combines information from different modalities using the path as an information carrier. Experimental results on real-world datasets demonstrate the superiority of PathFusion over state-of-the-art methods, with 22.4%-28.9% absolute improvement on Hits@1, and 0.194-0.245 absolute improvement on MRR.

翻译：实体对齐（Entity Alignment, EA）的目标是从多个知识图谱（Knowledge Graphs, KGs）中识别等价实体对，从而构建更全面统一的知识图谱。现有EA方法主要关注知识图谱的结构模态，缺乏对多模态信息的探索。少数多模态EA方法在该领域做出了有益尝试，但仍存在两个不足：（1）模态建模不一致且效率低下——为每种模态设计复杂且不同的模型；（2）由于模态在EA中的异构性质，导致模态融合效果不佳。为应对这些挑战，我们提出PathFusion方法，包含两个核心组件：（1）MSP——一种统一建模方法，通过构建连接实体与模态节点的路径来表示多种模态，从而简化对齐过程；（2）IRF——一种迭代融合方法，以路径作为信息载体有效整合不同模态的信息。在真实数据集上的实验结果显示，PathFusion相较于最先进方法具有显著优势：在Hits@1指标上实现22.4%-28.9%的绝对提升，在MRR指标上实现0.194-0.245的绝对提升。