ReCDAP: Relation-Based Conditional Diffusion with Attention Pooling for Few-Shot Knowledge Graph Completion

TL;DR

ReCDAP introduces a relation-based conditional diffusion model with attention pooling to improve few-shot knowledge graph completion by effectively leveraging positive and negative triples.

Contribution

It proposes a novel diffusion approach that separately models positive and negative relations using attention pooling, advancing few-shot KG completion methods.

Findings

Outperforms existing methods on benchmark datasets

Achieves state-of-the-art performance in few-shot KG completion

Effectively leverages negative triples through diffusion modeling

Abstract

Knowledge Graphs (KGs), composed of triples in the form of (head, relation, tail) and consisting of entities and relations, play a key role in information retrieval systems such as question answering, entity search, and recommendation. In real-world KGs, although many entities exist, the relations exhibit a long-tail distribution, which can hinder information retrieval performance. Previous few-shot knowledge graph completion studies focused exclusively on the positive triple information that exists in the graph or, when negative triples were incorporated, used them merely as a signal to indicate incorrect triples. To overcome this limitation, we propose Relation-Based Conditional Diffusion with Attention Pooling (ReCDAP). First, negative triples are generated by randomly replacing the tail entity in the support set. By conditionally incorporating positive information in the KG and non-existent negative information into the diffusion process, the model separately estimates the latent distributions for positive and negative relations. Moreover, including an attention pooler enables the model to leverage the differences between positive and negative cases explicitly. Experiments on two widely used datasets demonstrate that our method outperforms existing approaches, achieving state-of-the-art performance. The code is available at https://github.com/hou27/ReCDAP-FKGC.