多模态知识图谱嵌入的模态感知负采样

Apr, 2023

多模态知识图谱嵌入的模态感知负采样

Modality-Aware Negative Sampling for Multi-modal Knowledge Graph Embedding

Yichi Zhang, Mingyang Chen, Wen Zhang

TL;DR本文提出了Modality-Aware Negative Sampling (MANS)方法，用于在多模态知识图嵌入（MMKGE）中生成负三元组以进行训练，同时保持轻量级和高效，以提高性能。实验结果表明，MANS优于现有的NS方法。

Abstract

negative sampling (NS) is widely used in knowledge graph embedding (KGE), which aims to generate negative triples to make a positive-negative contrast during training. However, existing NS methods are unsuitable