# Spectral Graph Attention Network with Fast Eigen-approximation

arXiv: https://arxiv.org/abs/2003.07450 · HTML: https://mlsanity.com/paper/2003.07450/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Mar 2020.

## Built on by (most cited first, 18 of 18)

- [Spectral Augmentation for Self-Supervised Learning on Graphs](https://mlsanity.com/paper/2210.00643/) (2022)
- [Graph Structural Attack by Perturbing Spectral Distance](https://mlsanity.com/paper/2111.00684/) (2021)
- [Semi-Supervised Hierarchical Graph Classification](https://mlsanity.com/paper/2206.05416/) (2022)
- [Knowledge Graph Completion with Counterfactual Augmentation](https://mlsanity.com/paper/2302.13083/) (2023)
- [Path-based Explanation for Knowledge Graph Completion](https://mlsanity.com/paper/2401.02290/) (2024)
- [Adversarial Attack Framework on Graph Embedding Models with Limited Knowledge](https://mlsanity.com/paper/2105.12419/) (2021)
- [Revisiting Adversarial Attacks on Graph Neural Networks for Graph Classification](https://mlsanity.com/paper/2208.06651/) (2022)
- [A Survey on Graph Classification and Link Prediction based on GNN](https://mlsanity.com/paper/2307.00865/) (2023)
- [A Simple Yet Effective SVD-GCN for Directed Graphs](https://mlsanity.com/paper/2205.09335/) (2022)
- [Query Driven-Graph Neural Networks for Community Search: From Non-Attributed, Attributed, to Interactive Attributed](https://mlsanity.com/paper/2104.03583/) (2021)
- [Improving Your Graph Neural Networks: A High-Frequency Booster](https://mlsanity.com/paper/2210.08251/) (2022)
- [Structure-Aware DropEdge Towards Deep Graph Convolutional Networks](https://mlsanity.com/paper/2306.12091/) (2023)
- [Anisotropic Multi-Scale Graph Convolutional Network for Dense Shape Correspondence](https://mlsanity.com/paper/2210.09466/) (2022)
- [Towards Lightweight Graph Neural Network Search with Curriculum Graph Sparsification](https://mlsanity.com/paper/2406.16357/) (2024)
- [Graph Contrastive Learning with Low-Rank Regularization and Low-Rank Attention for Noisy Node Classification](https://mlsanity.com/paper/2402.09600/) (2024)
- [Accelerating Sparse Graph Neural Networks with Tensor Core Optimization](https://mlsanity.com/paper/2412.12218/) (2024)
- [Separated Contrastive Learning for Matching in Cross-domain Recommendation with Curriculum Scheduling](https://mlsanity.com/paper/2502.16239/) (2025)
- [An Attention-Based Framework for Alzheimers Disease Classification Using Resting-State fMRI](https://mlsanity.com/paper/2607.26746/) (2026)

## Abstract (arXiv)

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.