TA-KAND: Two-stage Attention Triple Enhancement and U-KAN based Diffusion For Few-shot Knowledge Graph Completion

TL;DR

This paper introduces a novel few-shot knowledge graph completion framework that combines a two-stage attention triple enhancer with a U-KAN based diffusion model, effectively addressing the long-tailed distribution of relations.

Contribution

It presents a new framework integrating attention-based triple enhancement and diffusion modeling specifically designed for few-shot knowledge graph completion.

Findings

Significant improvement over existing methods on public datasets.

Effective handling of long-tailed relation distributions.

Enhanced performance in few-shot scenarios.

Abstract

Knowledge Graphs have become fundamental infrastructure for applications such as intelligent question answering and recommender systems due to their expressive representation. Nevertheless, real-world knowledge is heterogeneous, leading to a pronounced long-tailed distribution over relations. Previous studies mainly based on metric matching or meta learning. However, they often overlook the distributional characteristics of positive and negative triple samples. In this paper, we propose a few-shot knowledge graph completion framework that integrates two-stage attention triple enhancer with U-KAN based diffusion model. Extensive experiments on two public datasets show significant advantages of our methods.