Self-supervised Graph Neural Networks without explicit negative sampling
This addresses the challenge of expensive manual labeling for graph data by providing an efficient unsupervised method, though it is incremental as it builds on existing contrastive learning and GNN techniques.
The authors tackled the problem of unsupervised learning on graph data by proposing SelfGNN, a self-supervised graph neural network that eliminates explicit negative sampling and uses feature augmentation, achieving performance comparable to state-of-the-art supervised GNNs and outperforming semi-supervised and unsupervised methods on seven real-world datasets.
Real world data is mostly unlabeled or only few instances are labeled. Manually labeling data is a very expensive and daunting task. This calls for unsupervised learning techniques that are powerful enough to achieve comparable results as semi-supervised/supervised techniques. Contrastive self-supervised learning has emerged as a powerful direction, in some cases outperforming supervised techniques. In this study, we propose, SelfGNN, a novel contrastive self-supervised graph neural network (GNN) without relying on explicit contrastive terms. We leverage Batch Normalization, which introduces implicit contrastive terms, without sacrificing performance. Furthermore, as data augmentation is key in contrastive learning, we introduce four feature augmentation (FA) techniques for graphs. Though graph topological augmentation (TA) is commonly used, our empirical findings show that FA perform as good as TA. Moreover, FA incurs no computational overhead, unlike TA, which often has O(N^3) time complexity, N-number of nodes. Our empirical evaluation on seven publicly available real-world data shows that, SelfGNN is powerful and leads to a performance comparable with SOTA supervised GNNs and always better than SOTA semi-supervised and unsupervised GNNs. The source code is available at https://github.com/zekarias-tilahun/SelfGNN.