LGOct 21, 2024

Deep Graph Attention Networks

arXiv:2410.15640v1Has Code2024 Twelfth International Symposium on Computing and Networking Workshops (CANDARW)
Originality Incremental advance
AI Analysis

This addresses a key bottleneck in graph attention networks (GATs) for researchers and practitioners, offering a time-saving solution to enhance GNN performance, though it appears incremental as it builds on existing GAT methods.

The paper tackles the over-smoothing problem in graph neural networks (GNNs), where node representations become similar across classes as layers increase, by introducing DeepGAT, a method that prevents over-smoothing and enables training a 15-layer network without tuning layers, achieving similar performance to a 2-layer GAT.

Graphs are useful for representing various realworld objects. However, graph neural networks (GNNs) tend to suffer from over-smoothing, where the representations of nodes of different classes become similar as the number of layers increases, leading to performance degradation. A method that does not require protracted tuning of the number of layers is needed to effectively construct a graph attention network (GAT), a type of GNN. Therefore, we introduce a method called "DeepGAT" for predicting the class to which nodes belong in a deep GAT. It avoids over-smoothing in a GAT by ensuring that nodes in different classes are not similar at each layer. Using DeepGAT to predict class labels, a 15-layer network is constructed without the need to tune the number of layers. DeepGAT prevented over-smoothing and achieved a 15-layer GAT with similar performance to a 2-layer GAT, as indicated by the similar attention coefficients. DeepGAT enables the training of a large network to acquire similar attention coefficients to a network with few layers. It avoids the over-smoothing problem and obviates the need to tune the number of layers, thus saving time and enhancing GNN performance.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes