COSTA: Covariance-Preserving Feature Augmentation for Graph Contrastive Learning
This work addresses a bottleneck in graph representation learning for tasks like node classification, but it is incremental as it builds on existing contrastive learning methods.
The paper tackled the problem of biased node embeddings in graph contrastive learning by proposing COSTA, a covariance-preserving feature augmentation framework, which achieved comparable or better results than graph augmentation-based models.
Graph contrastive learning (GCL) improves graph representation learning, leading to SOTA on various downstream tasks. The graph augmentation step is a vital but scarcely studied step of GCL. In this paper, we show that the node embedding obtained via the graph augmentations is highly biased, somewhat limiting contrastive models from learning discriminative features for downstream tasks. Thus, instead of investigating graph augmentation in the input space, we alternatively propose to perform augmentations on the hidden features (feature augmentation). Inspired by so-called matrix sketching, we propose COSTA, a novel COvariance-preServing feaTure space Augmentation framework for GCL, which generates augmented features by maintaining a "good sketch" of original features. To highlight the superiority of feature augmentation with COSTA, we investigate a single-view setting (in addition to multi-view one) which conserves memory and computations. We show that the feature augmentation with COSTA achieves comparable/better results than graph augmentation based models.