DANS-KGC: Diffusion Based Adaptive Negative Sampling for Knowledge Graph Completion

TL;DR

DANS-KGC introduces a diffusion-based adaptive negative sampling method that dynamically assesses and generates negative samples of varying difficulty, significantly improving knowledge graph completion performance.

Contribution

It proposes a novel diffusion-based negative sampling framework with difficulty-aware noise scheduling and dynamic training, addressing limitations of existing strategies.

Findings

Achieves state-of-the-art results on UMLS and YAGO3-10 datasets.

Effectively balances negative sample hardness during training.

Demonstrates strong generalization across multiple benchmarks.

Abstract

Negative sampling (NS) strategies play a crucial role in knowledge graph representation. In order to overcome the limitations of existing negative sampling strategies, such as vulnerability to false negatives, limited generalization, and lack of control over sample hardness, we propose DANS-KGC (Diffusion-based Adaptive Negative Sampling for Knowledge Graph Completion). DANS-KGC comprises three key components: the Difficulty Assessment Module (DAM), the Adaptive Negative Sampling Module (ANS), and the Dynamic Training Mechanism (DTM). DAM evaluates the learning difficulty of entities by integrating semantic and structural features. Based on this assessment, ANS employs a conditional diffusion model with difficulty-aware noise scheduling, leveraging semantic and neighborhood information during the denoising phase to generate negative samples of diverse hardness. DTM further enhances learning by dynamically adjusting the hardness distribution of negative samples throughout training, enabling a curriculum-style progression from easy to hard examples. Extensive experiments on six benchmark datasets demonstrate the effectiveness and generalization ability of DANS-KGC, with the method achieving state-of-the-art results on all three evaluation metrics for the UMLS and YAGO3-10 datasets.