Gated Graph Attention Networks with Learnable Temperature

2026-05-28

AI Summary

Standard graph attention networks struggle with unreliable node features and fixed sharpness in their attention distributions, which limits robustness in noisy environments. This work proposes a gated graph attention mechanism that employs learnable gates to filter out unreliable features or messages and introduces a learnable temperature parameter to dynamically adjust the sharpness of the attention distribution. By doing so, the method significantly enhances robustness against both feature perturbations and global noise while preserving model expressiveness. Experimental results demonstrate that the proposed model consistently outperforms baseline approaches on both homophilic and heterophilic graph benchmarks and exhibits markedly improved robustness under various noise conditions.

Abstract

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.

Problem

• graph attention networks
• unreliable features
• attention sharpness
• feature robustness
• heterophilic graphs

Innovation

• gated graph attention
• learnable temperature
• graph attention networks
• feature robustness
• attention sharpness