Back to Search Start Over

Not All Negatives Are Worth Attending to: Meta-Bootstrapping Negative Sampling Framework for Link Prediction

Authors :
Wang, Yakun
Hu, Binbin
Yang, Shuo
Zhu, Meiqi
Zhang, Zhiqiang
Zhang, Qiyang
Zhou, Jun
Ye, Guo
He, Huimei
Publication Year :
2023

Abstract

The rapid development of graph neural networks (GNNs) encourages the rising of link prediction, achieving promising performance with various applications. Unfortunately, through a comprehensive analysis, we surprisingly find that current link predictors with dynamic negative samplers (DNSs) suffer from the migration phenomenon between "easy" and "hard" samples, which goes against the preference of DNS of choosing "hard" negatives, thus severely hindering capability. Towards this end, we propose the MeBNS framework, serving as a general plugin that can potentially improve current negative sampling based link predictors. In particular, we elaborately devise a Meta-learning Supported Teacher-student GNN (MST-GNN) that is not only built upon teacher-student architecture for alleviating the migration between "easy" and "hard" samples but also equipped with a meta learning based sample re-weighting module for helping the student GNN distinguish "hard" samples in a fine-grained manner. To effectively guide the learning of MST-GNN, we prepare a Structure enhanced Training Data Generator (STD-Generator) and an Uncertainty based Meta Data Collector (UMD-Collector) for supporting the teacher and student GNN, respectively. Extensive experiments show that the MeBNS achieves remarkable performance across six link prediction benchmark datasets.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2312.04815
Document Type :
Working Paper