Representation Learning on Heterophilic Graph with Directional Neighborhood Attention
원문 초록
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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Following the Clues: Experiments on Person Re-ID using Cross-Modal Intelligence
AST-Enhanced or AST-Overloaded? The Surprising Impact of Hybrid Graph Representations on Code Clone Detection
Catching Bid-rigging Cartels with Graph Attention Neural Networks
Task-Agnostic Contrastive Pretraining for Relational Deep Learning
ST-GraphNet: A Spatio-Temporal Graph Neural Network for Understanding and Predicting Automated Vehicle Crash Severity
Topology-Aware Graph Neural Network-based State Estimation for PMU-Unobservable Power Systems
토론
이 논문과 연결된 포럼 글이 아직 없습니다.