通过交替约束优化实现结构特征对齐的图学习
Decoupled Structure-Feature Alignment via Alternating Optimization for Graph Learning
浏览论文内容
中文总结 AI 辅助
该研究针对传统GNN问题，引入约束双视图框架，利用锚定网络捕获特征，提出CSAG-GNN及循环交替优化策略，在节点预测中实现结构特征对齐，实证结果显示相比基线有性能提升和结构稳健性。
中文摘要 AI 辅助
我们引入了一个用于节点预测的约束双视图框架，将结构条件下的图神经网络（GNN）嵌入与由锚定模型学习的无结构特征先验对齐。传统GNN耦合特征变换和邻域聚合，易受拓扑噪声和异质连接影响。我们的框架利用独立锚定网络通过自监督重建目标捕获内在属性特征，还提出通道分割自适应门控GNN（CSAG-GNN），通过节点级门控机制在全局谱平滑和局部空间判别之间动态路由表示。我们提出稳定的循环交替优化策略解决耦合双级目标，防止训练中相互表示漂移。在同质性和异质性基准上的实证结果表明，相对于竞争基线，性能有平衡提升且结构稳健。
英文摘要
Conventional Graph Neural Networks (GNNs) couple feature transformation and neighborhood aggregation, which often renders them vulnerable to topological noise and heterophilous connections. To decouple this dependency, we present a constrained two-view learning framework for robust graph learning, which aligns structure-aware GNN embeddings with a structure-free feature prior. Specifically, the proposed Decoupled Structure-Feature Alternating Learning (DSAL) framework trains an independent anchor network using a self-supervised reconstruction objective to capture the intrinsic semantic information contained in node attributes. Within DSAL, to effectively integrate this prior, we design a channel-split adaptive gated (CSAG) layer. This architecture employs a gating mechanism to balance global spectral smoothing and local spatial representation dynamically. Furthermore, the model is optimized via a cyclic alternating procedure, which mitigates representation drift caused by mutual interference in standard joint optimization schemes. Experiments on diverse homophilous and heterophilous datasets suggest that our proposed approach provides improved node classification accuracy while maintaining robustness to structural perturbations compared to standard message-passing architectures.
发表机构
- College of Artificial Intelligence, Shaoxing Institute of Technology（绍兴文理学院人工智能学院）
- School of Mathematics and Computational Science, Xiangtan University（湘潭大学数学与计算科学学院）
机构由 AI 辅助整理，请以论文原文为准。
