通过注意力去噪学习图结构，提升节点分类准确率
Weighted Graph Structure Learning with Attention Denoising for Node Classification
- 用节点特征与边权重联合调整注意力系数
- 在多个数据集上平均提升17.8%的Micro-F1
- 适合处理带噪声边权的复杂图数据
图上的节点分类旨在利用少量已标注节点预测未标注节点的类别。然而，加权图常包含噪声边和异常边权重，会扭曲节点间的细粒度关系，影响分类准确性。本文提出边权重感知的图结构学习方法（EWGSL），融合边权重学习与图结构学习，改进图注意力网络中的注意力系数，使其同时考虑节点特征与边权重。该方法还通过图结构学习稀疏化注意力系数，并采用改进的InfoNCE损失函数，使模型适应去噪后的图权重。大量实验表明，相比最优基线，EWGSL在多个数据集上的平均Micro-F1提升达17.8%。
原文摘要 · Abstract (English)
Node classification in graphs aims to predict the categories of unlabeled nodes by utilizing a small set of labeled nodes. However, weighted graphs often contain noisy edges and anomalous edge weights, which can distort fine-grained relationships between nodes and hinder accurate classification. We propose the Edge Weight-aware Graph Structure Learning (EWGSL) method, which combines weight learning and graph structure learning to address these issues. EWGSL improves node classification by redefining attention coefficients in graph attention networks to incorporate node features and edge weights. It also applies graph structure learning to sparsify attention coefficients and uses a modified InfoNCE loss function to enhance performance by adapting to denoised graph weights. Extensive experimental results show that EWGSL has an average Micro-F1 improvement of 17.8% compared with the best baseline.
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。