SAIL: Self-Augmented Graph Contrastive Learning
DOI:
https://doi.org/10.1609/aaai.v36i8.20875Keywords:
Machine Learning (ML), Data Mining & Knowledge Management (DMKM)Abstract
This paper studies learning node representations with graph neural networks (GNNs) for unsupervised scenario. Specifically, we derive a theoretical analysis and provide an empirical demonstration about the non-steady performance of GNNs over different graph datasets, when the supervision signals are not appropriately defined. The performance of GNNs depends on both the node feature smoothness and the locality of graph structure. To smooth the discrepancy of node proximity measured by graph topology and node feature, we proposed SAIL - a novel self-augmented graph contrastive learning framework, with two complementary self-distilling regularization modules, i.e., intra- and inter-graph knowledge distillation. We demonstrate the competitive performance of SAIL on a variety of graph applications. Even with a single GNN layer, SAIL has consistently competitive or even better performance on various benchmark datasets, comparing with state-of-the-art baselines.Downloads
Published
2022-06-28
How to Cite
Yu, L., Pei, S., Ding, L., Zhou, J., Li, L., Zhang, C., & Zhang, X. (2022). SAIL: Self-Augmented Graph Contrastive Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 36(8), 8927-8935. https://doi.org/10.1609/aaai.v36i8.20875
Issue
Section
AAAI Technical Track on Machine Learning III