ReCDAP: Relation-Based Conditional Diffusion with Attention Pooling for Few-Shot Knowledge Graph Completion
This addresses the long-tail distribution of relations in knowledge graphs, improving information retrieval for tasks like question answering, but it is incremental as it builds on prior few-shot methods.
The paper tackles the problem of few-shot knowledge graph completion by proposing ReCDAP, which uses conditional diffusion with attention pooling to separately model positive and negative triples, achieving state-of-the-art performance on two datasets.
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.