Beyond Triplet Plausibility: Relation Set Completion in Knowledge Graphs

2026-06-29

AI Summary

This work addresses a key limitation in traditional knowledge graph completion, which focuses primarily on individual triple prediction while neglecting the semantic compatibility between entities and their potential relations. To overcome this, we introduce Relation Set Completion (RSC), a novel task that elevates the completion granularity from single triples to sets of relations associated with an entity. RSC leverages intrinsic patterns among an entity’s known relations to infer missing yet semantically compatible ones. We propose RelSetE, a relation set embedding model specifically designed for this task, and evaluate it on a new benchmark dataset constructed from standard knowledge graphs. Experimental results demonstrate that RelSetE effectively captures entity–relation compatibility and significantly outperforms existing methods on relation set completion.

Abstract

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.

Problem

• knowledge graph completion
• relation set completion
• entity-relation compatibility
• link prediction
• triplet prediction

Innovation

• relation set completion
• knowledge graph completion
• entity-relation compatibility
• RelSetE
• link prediction