mlsanityData to 7 Oct 2026

Fast Graph Attention Networks Using Effective Resistance Based Graph Sparsification

arXiv 2006.08796 ↗First posted 15 Jun 2020cs.LG stat.MLcited by 16

Not on the map. Why?

Abstract (arXiv)

The attention mechanism has demonstrated superior performance for inference over nodes in graph neural networks (GNNs), however, they result in a high computational burden during both training and inference. We propose FastGAT, a method to make attention based GNNs lightweight by using spectral sparsification to generate an optimal pruning of the input graph. This results in a per-epoch time that is almost linear in the number of graph nodes as opposed to quadratic. We theoretically prove that spectral sparsification preserves the features computed by the GAT model, thereby justifying our algorithm. We experimentally evaluate FastGAT on several large real world graph datasets for node classification tasks under both inductive and transductive settings. FastGAT can dramatically reduce (up to 10x) the computational time and memory requirements, allowing the usage of attention based GNNs on large graphs.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). First posted on arXiv 15 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 2; 2023: 5; 2024: 6; 2025: 2.

16 papers.

Sort:

  1. 2023NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classificationcited by 207
  2. 2022Survey on Graph Neural Network Acceleration: An Algorithmic Perspectivecited by 26
  3. 2023Data-centric Graph Learning: A Surveycited by 22
  4. 2024Sketch-GNN: Scalable Graph Neural Networks with Sublinear Training Complexitycited by 14
  5. 2024Efficient Topology-aware Data Augmentation for High-Degree Graph Neural Networkscited by 6
  6. 2024Sparse Covariance Neural Networkscited by 6
  7. 2024Can Graph Reordering Speed Up Graph Neural Network Training? An Experimental Studycited by 4
  8. 2024Unifews: You Need Fewer Operations for Efficient Graph Neural Networkscited by 2
  9. 2021LSP : Acceleration and Regularization of Graph Neural Networks via Locality Sensitive Pruning of Graphscited by 1
  10. 2022Rethinking Efficiency and Redundancy in Training Large-scale Graphscited by 1
  11. 2024On the Feasibility of Fidelity^- for Graph Pruningcited by 1
  12. 2025UEChecker: Detecting Unchecked External Call Vulnerabilities in DApps via Graph Analysiscited by 1
4 more
  1. 2023Graph Enabled Cross-Domain Knowledge Transfercited by 0
  2. 2023Fast and Effective GNN Training through Sequences of Random Path Graphscited by 0
  3. 2023Infinite Width Graph Neural Networks for Node Regression/ Classificationcited by 0
  4. 2025Theoretical Learning Performance of Graph Neural Networks: The Impact of Jumping Connections and Layer-wise Sparsificationcited by 0