CoATA: Effective Co-Augmentation of Topology and Attribute for Graph Neural Networks
It addresses a domain-specific issue of improving GNN robustness for graph learning tasks, representing an incremental advance by integrating existing techniques like contrastive learning.
The paper tackles the problem of noise and incompleteness in real-world graphs degrading Graph Neural Networks (GNNs) performance by proposing CoATA, a dual-channel framework for co-augmenting topology and attributes, which outperforms eleven state-of-the-art baselines on seven benchmark datasets.
Graph Neural Networks (GNNs) have garnered substantial attention due to their remarkable capability in learning graph representations. However, real-world graphs often exhibit substantial noise and incompleteness, which severely degrades the performance of GNNs. Existing methods typically address this issue through single-dimensional augmentation, focusing either on refining topology structures or perturbing node attributes, thereby overlooking the deeper interplays between the two. To bridge this gap, this paper presents CoATA, a dual-channel GNN framework specifically designed for the Co-Augmentation of Topology and Attribute. Specifically, CoATA first propagates structural signals to enrich and denoise node attributes. Then, it projects the enhanced attribute space into a node-attribute bipartite graph for further refinement or reconstruction of the underlying structure. Subsequently, CoATA introduces contrastive learning, leveraging prototype alignment and consistency constraints, to facilitate mutual corrections between the augmented and original graphs. Finally, extensive experiments on seven benchmark datasets demonstrate that the proposed CoATA outperforms eleven state-of-the-art baseline methods, showcasing its effectiveness in capturing the synergistic relationship between topology and attributes.