Contrastive General Graph Matching with Adaptive Augmentation Sampling
This work addresses the problem of graph matching for pattern recognition applications, offering a more effective and general approach, though it appears incremental as it builds on existing self-supervised techniques.
The paper tackles the problem of graph matching by addressing the limitations of supervised learning and self-supervised methods that require extensive labeled data or side information, introducing a novel contrastive framework with adaptive augmentation sampling that surpasses state-of-the-art self-supervised methods across various datasets.
Graph matching has important applications in pattern recognition and beyond. Current approaches predominantly adopt supervised learning, demanding extensive labeled data which can be limited or costly. Meanwhile, self-supervised learning methods for graph matching often require additional side information such as extra categorical information and input features, limiting their application to the general case. Moreover, designing the optimal graph augmentations for self-supervised graph matching presents another challenge to ensure robustness and efficacy. To address these issues, we introduce a novel Graph-centric Contrastive framework for Graph Matching (GCGM), capitalizing on a vast pool of graph augmentations for contrastive learning, yet without needing any side information. Given the variety of augmentation choices, we further introduce a Boosting-inspired Adaptive Augmentation Sampler (BiAS), which adaptively selects more challenging augmentations tailored for graph matching. Through various experiments, our GCGM surpasses state-of-the-art self-supervised methods across various datasets, marking a significant step toward more effective, efficient and general graph matching.