Spectral Graph Attention Network with Fast Eigen-approximation
This work addresses computational efficiency and global information capture in graph representation learning, offering an incremental improvement over existing GNN methods.
The paper tackles the problem of Graph Neural Networks (GNNs) being computationally expensive and limited to local information by introducing a spectral domain attention mechanism, resulting in SpGAT and SpGAT-Cheby that achieve better global pattern capture with fewer parameters and reduced computational costs, as verified in semi-supervised node classification tasks.
Variants of Graph Neural Networks (GNNs) for representation learning have been proposed recently and achieved fruitful results in various fields. Among them, Graph Attention Network (GAT) first employs a self-attention strategy to learn attention weights for each edge in the spatial domain. However, learning the attentions over edges can only focus on the local information of graphs and greatly increases the computational costs. In this paper, we first introduce the attention mechanism in the spectral domain of graphs and present Spectral Graph Attention Network (SpGAT) that learns representations for different frequency components regarding weighted filters and graph wavelets bases. In this way, SpGAT can better capture global patterns of graphs in an efficient manner with much fewer learned parameters than that of GAT. Further, to reduce the computational cost of SpGAT brought by the eigen-decomposition, we propose a fast approximation variant SpGAT-Cheby. We thoroughly evaluate the performance of SpGAT and SpGAT-Cheby in semi-supervised node classification tasks and verify the effectiveness of the learned attentions in the spectral domain.