提出可学习温度的门控图注意力，提升模型对噪声特征的鲁棒性。
Gated Graph Attention Networks with Learnable Temperature
- 引入门控机制过滤不可靠特征维度，减少干扰。
- 可学习温度动态调节注意力分布尖锐度，适应不同噪声水平。
- 在同质与异质图数据上均显著提升基线性能，适合噪声敏感场景。
图注意力网络通过数据依赖的系数学习邻居重要性，但标准层缺乏对不可靠特征维度的显式控制，且注意力系数分布的尖锐度固定。本文提出门控图注意力与可学习温度，用于通用图注意力机制。门控图注意力通过过滤特征或消息响应，降低不可靠维度的影响；可学习温度则动态调整注意力系数分布的尖锐度。在同质与异质异构基准测试中，所提变体始终优于对应图注意力基线，受控噪声实验进一步验证其在特征扰动下的行为。理论分析表明，当仅部分特征坐标可靠时，门控能提升鲁棒性；当全局噪声削弱节点特征可区分性时，温度调节有益。
原文摘要 · Abstract (English)
Graph attention networks learn neighbor importance through data-dependent coefficients, but standard layers lack explicit control over unreliable feature dimensions and use fixed sharpness of attention coefficient distributions. This paper proposes gated graph attention and learnable temperature for common graph attention mechanisms. Gated graph attention filters feature or message responses to reduce the influence of unreliable dimensions, while learnable temperature dynamically adjusts the sharpness of the attention coefficient distribution. Experiments on homogeneous and heterophilic heterogeneous benchmarks show that the proposed variants consistently improve the corresponding graph attention backbones, and controlled noise studies further verify their behavior under feature perturbations. Theoretical analysis explains these results by showing that gating improves robustness when only part of the feature coordinates are reliable, while temperature is beneficial when global noise weakens the discriminability of node features.
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。