GIMM: InfoMin-Max for Automated Graph Contrastive Learning
This work addresses a key bottleneck in unsupervised graph representation learning for researchers and practitioners, though it is incremental as it builds on existing contrastive learning frameworks.
The paper tackles the problem of automated graph contrastive learning (GCL) methods losing essential information for downstream tasks by proposing GIMM, which combines InfoMin and InfoMax principles to prevent redundancy and information loss, achieving state-of-the-art results in node and graph classification tasks.
Graph contrastive learning (GCL) shows great potential in unsupervised graph representation learning. Data augmentation plays a vital role in GCL, and its optimal choice heavily depends on the downstream task. Many GCL methods with automated data augmentation face the risk of insufficient information as they fail to preserve the essential information necessary for the downstream task. To solve this problem, we propose InfoMin-Max for automated Graph contrastive learning (GIMM), which prevents GCL from encoding redundant information and losing essential information. GIMM consists of two major modules: (1) automated graph view generator, which acquires the approximation of InfoMin's optimal views through adversarial training without requiring task-relevant information; (2) view comparison, which learns an excellent encoder by applying InfoMax to view representations. To the best of our knowledge, GIMM is the first method that combines the InfoMin and InfoMax principles in GCL. Besides, GIMM introduces randomness to augmentation, thus stabilizing the model against perturbations. Extensive experiments on unsupervised and semi-supervised learning for node and graph classification demonstrate the superiority of our GIMM over state-of-the-art GCL methods with automated and manual data augmentation.