InfoGCL: Information-Aware Graph Contrastive Learning
This work addresses the problem of customizing graph contrastive learning models for specific tasks and datasets, offering a foundational framework that unifies existing methods.
The authors tackled the lack of a unified framework for graph contrastive learning by proposing InfoGCL, which uses an Information Bottleneck principle to minimize information loss during representation learning, and demonstrated that it significantly outperforms state-of-the-art methods on benchmark datasets.
Various graph contrastive learning models have been proposed to improve the performance of learning tasks on graph datasets in recent years. While effective and prevalent, these models are usually carefully customized. In particular, although all recent researches create two contrastive views, they differ greatly in view augmentations, architectures, and objectives. It remains an open question how to build your graph contrastive learning model from scratch for particular graph learning tasks and datasets. In this work, we aim to fill this gap by studying how graph information is transformed and transferred during the contrastive learning process and proposing an information-aware graph contrastive learning framework called InfoGCL. The key point of this framework is to follow the Information Bottleneck principle to reduce the mutual information between contrastive parts while keeping task-relevant information intact at both the levels of the individual module and the entire framework so that the information loss during graph representation learning can be minimized. We show for the first time that all recent graph contrastive learning methods can be unified by our framework. We empirically validate our theoretical analysis on both node and graph classification benchmark datasets, and demonstrate that our algorithm significantly outperforms the state-of-the-arts.