SEG:Seeds-Enhanced Iterative Refinement Graph Neural Network for Entity Alignment
This work addresses entity alignment for merging knowledge graphs, which is crucial for integrating diverse data sources, but it appears incremental as it builds on existing semi-supervised methods.
The paper tackles the problem of entity alignment across knowledge graphs with non-isomorphic neighborhood structures by proposing a soft label propagation framework with iterative seed enhancement and a bidirectional weighted joint loss function, achieving superior results on multiple datasets.
Entity alignment is crucial for merging knowledge across knowledge graphs, as it matches entities with identical semantics. The standard method matches these entities based on their embedding similarities using semi-supervised learning. However, diverse data sources lead to non-isomorphic neighborhood structures for aligned entities, complicating alignment, especially for less common and sparsely connected entities. This paper presents a soft label propagation framework that integrates multi-source data and iterative seed enhancement, addressing scalability challenges in handling extensive datasets where scale computing excels. The framework uses seeds for anchoring and selects optimal relationship pairs to create soft labels rich in neighborhood features and semantic relationship data. A bidirectional weighted joint loss function is implemented, which reduces the distance between positive samples and differentially processes negative samples, taking into account the non-isomorphic neighborhood structures. Our method outperforms existing semi-supervised approaches, as evidenced by superior results on multiple datasets, significantly improving the quality of entity alignment.