Negative samples selecting strategy for graph contrastive learning
Document Type
Article
Publication Date
10-1-2022
Abstract
Graph neural networks (GNNs) have emerged as a successful method on graph structured data. Limited by expensive labeled data, contrastive learning has been adopted to the graph domain. In most existing node-level graph contrastive learning methods, when applying contrastive learning to a certain unlabeled node (the center node), its corresponding “similar” node (positive sample) is usually generated by data augmentation. Other nodes in the graph are served as the “dissimilar” nodes (negative samples), which leads to two major problems. First, the computational cost can be prohibitively expensive, especially when the graph is large. Second, utilizing some nodes which share the same label with the center node as the negative samples will damage the learning process. Hence, to address these issues, we explore the feasibility of only sampling a part of nodes for graph contrastive learning process. And unlike the previous self-supervised contrastive methods, we use joint training to exploit supervised signals as much as possible in contrastive learning. Hence, we propose a Negative Samples Selecting Strategy to utilize the classification prediction to guide the selection of the negative samples for sampled nodes. Then, we further incorporate this strategy for performing contrastive learning on graphs and propose a framework named Graph Contrastive Learning with Negative Samples Selecting Strategy (GCNSS). We demonstrate that GCNSS can be trained much faster with much less computation memory than graph contrastive learning baselines, and GCNSS can effectively boost the performance of existing GNN models on semi-supervised node classification tasks across many different datasets. The code is in: https://github.com/MR9812/GCNSS.
Identifier
85139042251 (Scopus)
Publication Title
Information Sciences
External Full Text Location
https://doi.org/10.1016/j.ins.2022.09.024
ISSN
00200255
First Page
667
Last Page
681
Volume
613
Grant
61872161
Fund Ref
National Natural Science Foundation of China
Recommended Citation
Miao, Rui; Yang, Yintao; Ma, Yao; Juan, Xin; Xue, Haotian; Tang, Jiliang; Wang, Ying; and Wang, Xin, "Negative samples selecting strategy for graph contrastive learning" (2022). Faculty Publications. 2626.
https://digitalcommons.njit.edu/fac_pubs/2626
