通过联合优化图结构与节点属性，提升GNN在噪声数据下的表现
CoATA: Effective Co-Augmentation of Topology and Attribute for Graph Neural Networks
- 双通道协同增强：先用结构信息净化属性，再用属性重构结构
- 在7个基准数据集上超越11种先进方法，最高提升6.2%准确率
- 适合处理噪声大、不完整的现实图数据，如社交网络或知识图谱
图神经网络（GNN）因其强大的图表示学习能力受到广泛关注。然而，真实世界图常存在显著噪声和缺失，严重损害GNN性能。现有方法多采用单一维度的数据增强，仅关注结构或属性的改进，忽略了二者深层交互。为此，本文提出CoATA——一种专为拓扑与属性协同增强设计的双通道GNN框架。首先，利用结构信号传播来丰富并去噪节点属性；随后，将增强后的属性空间投影至节点-属性二分图中，进一步优化或重建底层结构。在此基础上，引入对比学习，通过原型对齐与一致性约束，实现增强图与原始图之间的相互校正。在七个基准数据集上的大量实验表明，所提出的CoATA优于十一种当前最优基线方法，充分验证了其在捕捉拓扑与属性协同关系方面的有效性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。