Principled Representation Learning for Entity Alignment
This work addresses the problem of entity alignment in knowledge graphs for researchers and practitioners by providing a more principled approach, though it is incremental as it builds on existing EEA methods.
The paper tackled the lack of understanding in embedding-based entity alignment (EEA) by analyzing the limitations of existing methods, which rely on a small number of pre-aligned entities without guaranteeing tight bounds for alignment learning, and proposed NeoEA to learn KG-invariant and principled embeddings, resulting in consistent and significant performance improvements over state-of-the-art EEA methods.
Embedding-based entity alignment (EEA) has recently received great attention. Despite significant performance improvement, few efforts have been paid to facilitate understanding of EEA methods. Most existing studies rest on the assumption that a small number of pre-aligned entities can serve as anchors connecting the embedding spaces of two KGs. Nevertheless, no one investigates the rationality of such an assumption. To fill the research gap, we define a typical paradigm abstracted from existing EEA methods and analyze how the embedding discrepancy between two potentially aligned entities is implicitly bounded by a predefined margin in the scoring function. Further, we find that such a bound cannot guarantee to be tight enough for alignment learning. We mitigate this problem by proposing a new approach, named NeoEA, to explicitly learn KG-invariant and principled entity embeddings. In this sense, an EEA model not only pursues the closeness of aligned entities based on geometric distance, but also aligns the neural ontologies of two KGs by eliminating the discrepancy in embedding distribution and underlying ontology knowledge. Our experiments demonstrate consistent and significant improvement in performance against the best-performing EEA methods.