HaSa: Hardness and Structure-Aware Contrastive Knowledge Graph Embedding
This addresses a bias issue in knowledge graph embedding for researchers and practitioners, but it is incremental as it builds on existing contrastive learning approaches.
The paper tackles the problem of false negative triples in knowledge graph embedding by proposing HaSa, a hardness and structure-aware contrastive method, which improves performance and achieves state-of-the-art results on WN18RR datasets and competitive results on FB15k-237 datasets.
We consider a contrastive learning approach to knowledge graph embedding (KGE) via InfoNCE. For KGE, efficient learning relies on augmenting the training data with negative triples. However, most KGE works overlook the bias from generating the negative triples-false negative triples (factual triples missing from the knowledge graph). We argue that the generation of high-quality (i.e., hard) negative triples might lead to an increase in false negative triples. To mitigate the impact of false negative triples during the generation of hard negative triples, we propose the Hardness and Structure-aware (\textbf{HaSa}) contrastive KGE method, which alleviates the effect of false negative triples while generating the hard negative triples. Experiments show that HaSa improves the performance of InfoNCE-based KGE approaches and achieves state-of-the-art results in several metrics for WN18RR datasets and competitive results for FB15k-237 datasets compared to both classic and pre-trained LM-based KGE methods.