StarGraph: Knowledge Representation Learning based on Incomplete Two-hop Subgraph
This addresses the limitation of ignoring neighborhood information in knowledge graph embeddings for researchers and practitioners in AI, though it is incremental as it builds on existing graph-based methods.
The paper tackles the problem of knowledge graph representation learning by proposing StarGraph, which uses incomplete two-hop neighborhood subgraphs processed with self-attention to incorporate neighborhood information, achieving state-of-the-art performance on ogbl-wikikg2 and competitive results on fb15k-237.
Conventional representation learning algorithms for knowledge graphs (KG) map each entity to a unique embedding vector, ignoring the rich information contained in the neighborhood. We propose a method named StarGraph, which gives a novel way to utilize the neighborhood information for large-scale knowledge graphs to obtain entity representations. An incomplete two-hop neighborhood subgraph for each target node is at first generated, then processed by a modified self-attention network to obtain the entity representation, which is used to replace the entity embedding in conventional methods. We achieved SOTA performance on ogbl-wikikg2 and got competitive results on fb15k-237. The experimental results proves that StarGraph is efficient in parameters, and the improvement made on ogbl-wikikg2 demonstrates its great effectiveness of representation learning on large-scale knowledge graphs. The code is now available at \url{https://github.com/hzli-ucas/StarGraph}.