# Centrality-Based Pruning for Efficient Echo State Networks

arXiv: https://arxiv.org/abs/2603.20684 · HTML: https://mlsanity.com/paper/2603.20684/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 35 references that are in the map.
- First posted on arXiv 21 Mar 2026.

## Builds on (most cited first, 5 of 5)

- [Relational inductive biases, deep learning, and graph networks](https://mlsanity.com/paper/1806.01261/) (2018)
- [Learning to Identify High Betweenness Centrality Nodes from Scratch: A Novel Graph Neural Network Approach](https://mlsanity.com/paper/1905.10418/) (2019)
- [Centrality Measures in Networks](https://mlsanity.com/paper/1608.05845/) (2016)
- [Investigating echo state networks dynamics by means of recurrence analysis](https://mlsanity.com/paper/1601.07381/) (2016)
- [Effective Fine-Tuning with Eigenvector Centrality Based Pruning](https://mlsanity.com/paper/2512.12543/) (2025)

## Built on by (most cited first, 1 of 1)

- [Rethinking Reservoir Pruning: A Dynamical Perspective for Echo State Networks](https://mlsanity.com/paper/2608.04593/) (2026)

## Abstract (arXiv)

Echo State Networks (ESNs) are a reservoir computing framework widely used for nonlinear time-series prediction. However, despite their effectiveness, randomly initialized reservoirs often contain redundant nodes, leading to unnecessary computational overhead and reduced efficiency. In this work, we propose a graph centrality-based pruning approach that interprets the reservoir as a weighted directed graph and removes structurally less important nodes using centrality measures. Experiments on Mackey-Glass time-series prediction and electric load forecasting demonstrate that the proposed method can significantly reduce reservoir size while maintaining, and in some cases improving, prediction accuracy.