Beyond Triplet Plausibility: Relation Set Completion in Knowledge Graphs
2026-06-29 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors point out that current methods for completing knowledge graphs mainly focus on predicting missing triplets but miss understanding which relations fit well with an entity as a whole. To fix this, they propose a new task called relation set completion, which tries to find all missing relations compatible with an entity. They also introduce a model named RelSetE that learns patterns among known relations to predict missing ones. Their experiments on new benchmark datasets show that RelSetE works well at capturing these compatibility patterns and improving relation prediction.
Knowledge GraphKnowledge Graph CompletionTriplet PredictionLink PredictionEntity-Relation CompatibilityRelation Set CompletionEmbedding ModelRelation Set EmbeddingBenchmark Dataset
Authors
Zihao Zheng, Borui Cai, Yao Zhao, Keshav Sood, Yong Xiang
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.