Centrality-Based Pruning for Efficient Echo State Networks

• URL: http://arxiv.org/abs/2603.20684v1
• Date: Sat, 21 Mar 2026 06:55:50 GMT
• Title: Centrality-Based Pruning for Efficient Echo State Networks
• Abstract summary: We propose a graph-based pruning approach that interprets the reservoir as a weighted directed graph and removes structurally less important nodes using centrality measures.<n> Experiments on Mackey-Glass time-series prediction and electric load forecasting demonstrate that the proposed method can significantly reduce reservoir size while maintaining centrality.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Echo State Networks (ESNs) are a reservoir computing framework widely used for nonlinear time-series prediction. However, despite their effectiveness, the randomly initialized reservoir often contains 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, while preserving the essential reservoir dynamics.

Related papers

• Rethinking Reservoir Pruning: A Dynamical Perspective for Echo State Networks [0.0]
  We propose Dynamical Mode Pruning (DMP), a reservoir pruning method that ranks neurons by their contribution to dominant transition modes.<n>DMP improves or preserves forecasting accuracy while reducing redundant reservoir components.
  arXiv  Detail & Related papers  (2026-08-05T08:56:17Z)
• GUIDED Network-Agnostic Feature Initialization for Spatial Transferability in GNN-based Models [46.28228608289378]
  The Traffic Assignment Problem is a fundamental but computationally expensive component of transportation planning.<n>This research proposes a network-agnostic initialization layer, termed Geometrically Unconstrained Inductive Demand EmbeDding.<n>This framework standardizes the input space regardless of network scale.<n>It provides a versatile blueprint for generalized origin-destination spatial problems, such as freight logistics and multimodal network optimization.
  arXiv  Detail & Related papers  (2026-07-21T16:41:59Z)
• Cascade-KDE: Robust Time-Series Restoration under Out-of-Distribution Impulse Corruptions [3.4633810891614267]
  Real-world time-series data in industrial sensing, healthcare, and energy systems is often corrupted by a mixture of Gaussian noise.<n>We propose Cascade-KDE, a training-free restoration framework for corrupted time series.
  arXiv  Detail & Related papers  (2026-05-22T00:59:56Z)
• Efficient Prompt Learning for Traffic Forecasting [78.86991846411793]
  We introduce a lightweight and model-agnostic prompt tuning framework for adapting pre-trained-temporal GNNs, named SimpleST.<n>It reduces the overhead and complexity of adaptation, enabling efficient utilization of pre-trained models for out-distribution generalization.
  arXiv  Detail & Related papers  (2026-05-08T03:45:51Z)
• Anticipating tipping in spatiotemporal systems with machine learning [0.0]
  We use a machine-learning framework of parameter-adaptable reservoir computing to accurately anticipate tipping in complex dynamical systems.<n>We demonstrate tipping can be identified within a prediction window across a variety of timetemporal dynamical systems, as well as in CMIP5Coupled Model Intercomparison Project 5 climate.
  arXiv  Detail & Related papers  (2026-04-07T20:51:58Z)
• FaST: Efficient and Effective Long-Horizon Forecasting for Large-Scale Spatial-Temporal Graphs via Mixture-of-Experts [49.9321870703948]
  Existing models predominantly focus on short-horizon predictions and suffer from notorious computational costs and memory consumption.<n>We present FaST, an effective and efficient framework based on Mixture-of-Experts (MoEs) for long-horizon and large-scale STG forecasting.<n>FaST is underpinned by two key innovations. First, an adaptive graph agent attention mechanism is proposed to alleviate the computational burden.<n>Second, we propose a new parallel MoE module that replaces traditional feed-forward networks with Gated Linear Units (GLUs)
  arXiv  Detail & Related papers  (2026-01-08T18:00:58Z)
• Dynamics-Informed Reservoir Computing with Visibility Graphs [0.0]
  Reservoir computing offers a computationally efficient alternative to traditional deep learning.<n>Despite its advantages, the largely random reservoir graph architecture often results in suboptimal networks with poorly understood dynamics.<n>We propose a novel Dynamics-Informed Reservoir Computing framework that systematically infers the reservoir network structure directly from the input training sequence.
  arXiv  Detail & Related papers  (2025-07-25T08:07:17Z)
• A tensor network approach for chaotic time series prediction [1.03590082373586]
  This paper explores the application of a previously proposed tensor network model for predicting chaotic time series.<n>It shows its advantages in terms of accuracy and computational efficiency compared to conventional echo state networks.<n>Using a state-of-the-art tensor network approach, we bridge the gap between the tensor network and reservoir computing communities.
  arXiv  Detail & Related papers  (2025-05-23T11:03:35Z)
• Fast Training of Recurrent Neural Networks with Stationary State Feedbacks [48.22082789438538]
  Recurrent neural networks (RNNs) have recently demonstrated strong performance and faster inference than Transformers.<n>We propose a novel method that replaces BPTT with a fixed gradient feedback mechanism.
  arXiv  Detail & Related papers  (2025-03-29T14:45:52Z)
• Self-supervised Multi-future Occupancy Forecasting for Autonomous Driving [31.995016095663544]
  LiDAR-generated occupancy grid maps (L-OGMs) offer a robust bird's-eye view for the scene representation.<n>Our proposed framework, Latent Occupancy Prediction (LOPR), performs L-OGM prediction in the latent space of a generative architecture.
  arXiv  Detail & Related papers  (2024-07-30T18:37:59Z)
• Physics-guided Active Sample Reweighting for Urban Flow Prediction [75.24539704456791]
  Urban flow prediction is a nuanced-temporal modeling that estimates the throughput of transportation services like buses, taxis and ride-driven models. Some recent prediction solutions bring remedies with the notion of physics-guided machine learning (PGML) We develop a atized physics-guided network (PN), and propose a data-aware framework Physics-guided Active Sample Reweighting (P-GASR)
  arXiv  Detail & Related papers  (2024-07-18T15:44:23Z)
• Reservoir computing with logistic map [0.0]
  We demonstrate here a method to predict temporal and nontemporal tasks by constructing virtual nodes as constituting a reservoir in reservoir computing. We predict three nonlinear systems, namely Lorenz, Rossler, and Hindmarsh-Rose, for temporal tasks and a seventh order for nontemporal tasks with great accuracy. Remarkably, the logistic map performs well and predicts close to the actual or target values.
  arXiv  Detail & Related papers  (2024-01-17T09:22:15Z)
• Attention-Enhanced Reservoir Computing [0.0]
  Photonic reservoir computing has been successfully utilized in time-series prediction. We introduce an attention mechanism to the reservoir computing model in the output stage. Our results show that a photonic reservoir computer enhanced with the attention mechanism exhibits improved prediction capabilities for smaller reservoirs.
  arXiv  Detail & Related papers  (2023-12-27T10:16:01Z)
• Precise characterization of the prior predictive distribution of deep ReLU networks [45.46732383818331]
  We derive a precise characterization of the prior predictive distribution of finite-width ReLU networks with Gaussian weights. Our results provide valuable guidance on prior design, for instance, controlling the predictive variance with depth- and width-informed priors on the weights of the network.
  arXiv  Detail & Related papers  (2021-06-11T21:21:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.