Beyond Triplet Plausibility: Relation Set Completion in Knowledge Graphs
For knowledge graph researchers, this work identifies a previously overlooked type of incompleteness and provides a new task and model, though the gains are incremental as it complements existing link prediction.
The paper introduces a new task, Relation Set Completion (RSC), to address the incompleteness of entity-relation compatibility in knowledge graphs, and proposes RelSetE, a model that infers missing relations by learning latent patterns from observed relations. Experiments on three derived benchmarks show RelSetE effectively captures these patterns and performs well.
Knowledge graphs (KGs) organize real-world knowledge as triplets and underpin many downstream applications. Due to their inherent incompleteness, knowledge graph completion (KGC) is widely studied and is typically formulated as triplet prediction, with link prediction as the dominant paradigm. However, this formulation focuses on the incompleteness of triplet-wise information and overlooks the incompleteness of entity-relation compatibility information. To address this limitation, we introduce a relation set completion task (RSC), which complements the link prediction task and aims to reason about missing relations that are semantically compatible with a given entity. We further propose a Relation Set Embedding model (RelSetE), which models latent patterns among the observed relations of entities to infer missing ones. To evaluate RelSetE, we derive three benchmark datasets from standard KG benchmarks. Extensive experiments demonstrate that RelSetE effectively captures entity-relation compatibility patterns and performs favorably in inferring missing relations of entities. Code and data are publicly available.