Graph Attention Network (GAT) is one of the most popular Graph Neural Network
(GNN) architecture, which employs the attention mechanism to learn edge weights
and has demonstrated promising performance in various applications. However,
since it only incorporates information from immediate neighborhood, it lacks
the ability to capture long-range and global graph information, leading to
unsatisfactory performance on some datasets, particularly on heterophilic
graphs. To address this limitation, we propose the Directional Graph Attention
Network (DGAT) in this paper. DGAT is able to combine the feature-based
attention with the global directional information extracted from the graph
topology. To this end, a new class of Laplacian matrices is proposed which can
provably reduce the diffusion distance between nodes. Based on the new
Laplacian, topology-guided neighbour pruning and edge adding mechanisms are
proposed to remove the noisy and capture the helpful long-range neighborhood
information. Besides, a global directional attention is designed to enable a
topological-aware information propagation. The superiority of the proposed DGAT
over the baseline GAT has also been verified through experiments on real-world
benchmarks and synthetic data sets. It also outperforms the state-of-the-art
(SOTA) models on 6 out of 7 real-world benchmark datasets.

提出了一种名为 Directional Graph Attention Network (DGAT) 的新型图神经网络结构，利用特征注意力和全局方向信息提高图信息的传播能力，并通过拓扑信息引导的节点剪枝和边添加机制以及新的拉普拉斯矩阵来改善 GAT 存在的局限性，实验证明在真实数据集和合成数据集上，DGAT 在性能上优于传统的 GAT 模型，并在 7 个真实数据集中的 6 个数据集上超越了现有的最先进模型。