Zhao, P., Pan, Y., Li, X., Chen, X., Tsang, I. W., & Liao, L. (2024). Coarse-to-Fine Contrastive Learning on Graphs. IEEE Transactions on Neural Networks and Learning Systems, 35(4), 4622–4634. https://doi.org/10.1109/tnnls.2022.3228556
Abstract:
Inspired by the impressive success of contrastive learning (CL), a variety of graph augmentation strategies have been employed to learn node representations in a self-supervised manner. Existing methods construct the contrastive samples by adding perturbations to the graph structure or node attributes. Although impressive results are achieved, it is rather blind to the wealth of prior information assumed: with the increase of the perturbation degree applied on the original graph, 1) the similarity between the original graph and the generated augmented graph gradually decreases; 2) the discrimination between all nodes within each augmented view gradually increases. In this paper, we argue that both such prior information can be incorporated (differently) into the contrastive learning paradigm following our general ranking framework. In particular, we first interpret CL as a special case of learning to rank (L2R), which inspires us to leverage the ranking order among positive augmented views. Meanwhile, we introduce a self-ranking paradigm to ensure that the discriminative information among different nodes can be maintained and also be less altered to the perturbations of different degrees. Experiment results on various benchmark datasets verify the effectiveness of our algorithm compared with the supervised and unsupervised models.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the Agency for Science, Technology and Research - Career Development Fund (CDF)
Grant Reference no. : C222812019
This research / project is supported by the Australian Research Council (ARC) - Discovery Projects
Grant Reference no. : DP200101328
This research / project is supported by the Ministry of Science and Technology (MOST) of CHINA - National Natural Science Foundation of China (NSFC)
Grant Reference no. : 92270125
This research / project is supported by the Ministry of Science and Technology (MOST) of CHINA - National Natural Science Foundation of China (NSFC)
Grant Reference no. : 62276024