Wiener Graph Deconvolutional Network Improves Graph Self-Supervised Learning

Graph self-supervised learning (SSL) has been vastly employed to learn representations from unlabeled graphs. Existing methods can be roughly divided into predictive learning and contrastive learning, where the latter one attracts more research attention with better empirical performance. We argue that, however, predictive models weaponed with powerful decoder could achieve comparable or even better representation power than contrastive models. In this work, we propose a Wiener Graph Deconvolutional Network (WGDN), an augmentation-adaptive decoder empowered by graph wiener filter to perform information reconstruction. Theoretical analysis proves the superior reconstruction ability of graph wiener filter. Extensive experimental results on various datasets demonstrate the effectiveness of our approach.

Authors

• Jiashun Cheng The Hong Kong University of Science and Technology
• Man Li The Hong Kong University of Science and Technology
• Jia Li School of Computer Science, Peking University MoE Key Lab. of High Confidence Software Technologies(PKU), China
• Fugee Tsung The Hong Kong University of Science and Technology (Guangzhou) The Hong Kong University of Science and Technology

Keywords

• ML: Graph-based Machine Learning
• ML: Unsupervised & Self-Supervised Learning