Dynamic Knowledge Graph Alignment


  • Yuchen Yan University of Illinois at Urbana-Champaign
  • Lihui Liu University of Illinois at Urbana-Champaign
  • Yikun Ban University of Illinois at Urbana-Champaign
  • Baoyu Jing University of Illinois at Urbana-Champaign
  • Hanghang Tong University of Illinois at Urbana-Champaign




Web Ontologies -- Creation, Extraction, Evolution


Knowledge graph (KG for short) alignment aims at building a complete KG by linking the shared entities across complementary KGs. Existing approaches assume that KGs are static, despite the fact that almost every KG evolves over time. In this paper, we introduce the task of dynamic knowledge graph alignment, the main challenge of which is how to efficiently update entity embeddings for the evolving graph topology. Our key insight is to view the parameter matrix of GCN as a feature transformation operator and decouple the transformation process from the aggregation process. Based on that, we first propose a novel base algorithm (DINGAL-B) with topology-invariant mask gate and highway gate, which consistently outperforms 14 existing knowledge graph alignment methods in the static setting. More importantly, it naturally leads to two effective and efficient algorithms to align dynamic knowledge graph, including (1) DINGAL-O which leverages previous parameter matrices to update the embeddings of affected entities; and (2) DINGAL-U which resorts to newly obtained anchor links to fine-tune parameter matrices. Compared with their static counterpart (DINGAL-B), DINGAL-U and DINGAL-O are 10× and 100× faster respectively, with little alignment accuracy loss.




How to Cite

Yan, Y., Liu, L., Ban, Y., Jing, B., & Tong, H. (2021). Dynamic Knowledge Graph Alignment. Proceedings of the AAAI Conference on Artificial Intelligence, 35(5), 4564-4572. https://doi.org/10.1609/aaai.v35i5.16585



AAAI Technical Track on Data Mining and Knowledge Management