# Spectral Theory for Edge Pruning in Asynchronous Recurrent Graph Neural Networks

arXiv: https://arxiv.org/abs/2502.17522 · HTML: https://mlsanity.com/paper/2502.17522/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 12 references that are in the map.
- First posted on arXiv 23 Feb 2025.

## Builds on (most cited first, 7 of 7)

- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [Pruning and Quantization for Deep Neural Network Acceleration: A Survey](https://mlsanity.com/paper/2101.09671/) (2021)
- [A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations](https://mlsanity.com/paper/2308.06767/) (2023)
- [Graph Clustering with Graph Neural Networks](https://mlsanity.com/paper/2006.16904/) (2020)
- [Manifold Regularized Dynamic Network Pruning](https://mlsanity.com/paper/2103.05861/) (2021)
- [Optimal Recurrent Network Topologies for Dynamical Systems Reconstruction](https://mlsanity.com/paper/2406.04934/) (2024)
- [Asynchronous Neural Networks for Learning in Graphs](https://mlsanity.com/paper/2205.12245/) (2022)

## Abstract (arXiv)

Graph Neural Networks (GNNs) have emerged as a powerful tool for learning on graph-structured data, finding applications in numerous domains including social network analysis and molecular biology. Within this broad category, Asynchronous Recurrent Graph Neural Networks (ARGNNs) stand out for their ability to capture complex dependencies in dynamic graphs, resembling living organisms' intricate and adaptive nature. However, their complexity often leads to large and computationally expensive models. Therefore, pruning unnecessary edges becomes crucial for enhancing efficiency without significantly compromising performance. This paper presents a dynamic pruning method based on graph spectral theory, leveraging the imaginary component of the eigenvalues of the network graph's Laplacian.