通过去噪提升知识图谱嵌入在噪声下的鲁棒性
Robust Knowledge Graph Embedding via Denoising
- 将嵌入模型视为能量模型，用去噪训练增强抗干扰能力
- 在扰动实体嵌入下，性能超越现有最优方法
- 提出基于随机平滑的可证明鲁棒性评估指标
我们关注嵌入空间中存在扰动时获取稳健的知识图谱嵌入。为应对这一挑战，提出一种新框架——基于去噪的鲁棒知识图谱嵌入（Robust Knowledge Graph Embedding via Denoising），以增强KGE模型对噪声三元组的鲁棒性。通过将KGE方法视为能量基模型，利用去噪与评分匹配之间的已有联系，实现鲁棒去噪KGE模型的训练。此外，基于随机平滑概念，提出针对KGE方法的可证明鲁棒性评估指标。在基准数据集上的大量实验表明，面对扰动的实体嵌入，该框架始终优于现有最先进KGE方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。