用图中心性剪枝提升时序预测的脉冲网络效率
Centrality-Based Pruning for Efficient Echo State Networks
- 将脉冲网络视为加权有向图，按节点重要性剪枝
- 剪枝后模型体积减小，预测精度反而提升或保持
- 适合需要高效时序建模的工程应用
脉冲状态网络（ESN）是一种广泛用于非线性时间序列预测的储备计算框架。尽管效果显著，但随机初始化的储备池常包含冗余节点，造成不必要的计算开销并降低效率。本文提出一种基于图中心性的剪枝方法，将储备池视为加权有向图，利用中心性度量识别并移除结构上不重要的节点。在Mackey-Glass时间序列预测和电力负荷预测任务上的实验表明，该方法可显著缩小储备池规模，同时保持甚至在某些情况下提升预测精度。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。