Robust Knowledge Graph Embedding via Denoising

Authors:
  • TSTengwei Song
    Tengwei Song
  • XMXudong Ma
    Xudong Ma
  • YLYang Liu
    Yang Liu
  • JLJie Luo
    Jie Luo

Abstract
We focus on obtaining robust knowledge graph embedding under perturbation in the embedding space. To address these challenges, we introduce a novel framework, Robust Knowledge Graph Embedding via Denoising, which enhances the robustness of KGE models on noisy triples. By treating KGE methods as energy-based models, we leverage the established connection between denoising and score matching, enabling the training of a robust denoising KGE model. Furthermore, we propose certified robustness evaluation metrics for KGE methods based on the concept of randomized smoothing. Through comprehensive experiments on benchmark datasets, our framework consistently shows superior performance compared to existing state-of-the-art KGE methods when faced with perturbed entity embedding.
All Related Versions