CoCo: A Coupled Contrastive Framework for Unsupervised Domain Adaptive Graph Classification
This work addresses the challenge of applying graph neural networks to domain adaptation without labeled data, which is an incremental improvement for researchers in graph learning and domain adaptation.
The paper tackles the problem of unsupervised domain adaptation for graph classification by proposing CoCo, a coupled contrastive framework that extracts topological information and reduces domain discrepancy, achieving superior performance over baselines in experiments on popular datasets.
Although graph neural networks (GNNs) have achieved impressive achievements in graph classification, they often need abundant task-specific labels, which could be extensively costly to acquire. A credible solution is to explore additional labeled graphs to enhance unsupervised learning on the target domain. However, how to apply GNNs to domain adaptation remains unsolved owing to the insufficient exploration of graph topology and the significant domain discrepancy. In this paper, we propose Coupled Contrastive Graph Representation Learning (CoCo), which extracts the topological information from coupled learning branches and reduces the domain discrepancy with coupled contrastive learning. CoCo contains a graph convolutional network branch and a hierarchical graph kernel network branch, which explore graph topology in implicit and explicit manners. Besides, we incorporate coupled branches into a holistic multi-view contrastive learning framework, which not only incorporates graph representations learned from complementary views for enhanced understanding, but also encourages the similarity between cross-domain example pairs with the same semantics for domain alignment. Extensive experiments on popular datasets show that our CoCo outperforms these competing baselines in different settings generally.