Centrality-Based Pruning for Efficient Echo State Networks

TL;DR

This paper introduces a graph centrality-based pruning method for Echo State Networks that reduces reservoir size and computational cost while maintaining or improving prediction accuracy.

Contribution

It proposes a novel reservoir pruning technique based on graph centrality measures, enhancing ESN efficiency without sacrificing performance.

Findings

Significant reservoir size reduction achieved

Prediction accuracy maintained or improved

Method effective on time-series forecasting tasks

Abstract

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.