Wiener Graph Deconvolutional Network Improves Graph Self-Supervised Learning
This work addresses graph representation learning for unlabeled data, offering a predictive alternative to contrastive methods, but it appears incremental as it builds on existing predictive learning frameworks.
The paper tackles the problem of graph self-supervised learning by proposing a Wiener Graph Deconvolutional Network (WGDN), which uses a graph wiener filter for information reconstruction, achieving comparable or better performance than contrastive models on various datasets.
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.