Few-Shot Knowledge Graph Completion With Star and Ring Topology Information Aggregation

Few-shot knowledge graph completion (FKGC) addresses the long-tail problem of relations by leveraging a few observed support entity pairs to infer unknown facts for tail-located relations. Learning the relation representation of entity pairs and evaluating the match of query and support entity pairs are the two key steps of FKGC. Existing methods learn the representation of entity pairs by either aggregating neighbors of entities or integrating relation representations in the connected paths from head to tail. However, in few-shot scenarios, the limited number of support entity pairs and insufficient structural information with a single neighborhood topology will lead to matching failure. To this end, we consider the star and ring topological information for a given entity pair: (1) Entity neighborhood, which captures multi-hop neighbors of entities; (2) Relational path, which characterizes compound relation forms. Furthermore, to effectively fuse the two kinds of heterogeneous topological information, we design the multi-aggregator and the fine-grained path correlation matching algorithm to obtain more delicate and balanced matching. Based on the proposed relational path correlation matching module, we propose the relation adaptive network to solve the few-shot temporal knowledge graph completion problem. The experimental results show that our method continuously outperforms the state-of-the-art methods.

I. Introduction

Knowledge graphs (KGs) have facilitated many real-world applications [1], [2], [3], [4]. However, they are often incomplete, which limits the performance and range of KG-based applications in downstream tasks. Therefore, knowledge graph completion (KGC) methods that aim to infer the missing facts from the existing facts automatically have become the focus of current research. Among them, the embedding-based KGC methods [5], [6] have been proven effective, which map entities and relations to low-dimensional representations and use these representations to predict missing facts.