TS-LIF: A Temporal Segment Spiking Neuron Network for Time Series Forecasting

2025-03-07

AI Summary

Traditional Leaky Integrate-and-Fire (LIF) neurons struggle to capture long-term dependencies and multi-scale temporal dynamics, limiting their effectiveness in time-series forecasting. To address this, we propose the Temporal-Scale LIF (TS-LIF) spiking neuron model, featuring a novel dual-compartment functional heterogeneity: dendrites specialize in high-frequency response, while the soma governs low-frequency integration. TS-LIF introduces direct somatic current injection and dendritic spike generation to enhance signal fidelity and multi-scale feature extraction. Built upon an enhanced LIF framework, it integrates dynamical stability analysis, frequency-domain response modeling, and end-to-end differentiable training. Extensive experiments on multiple benchmark time-series datasets demonstrate that TS-LIF significantly outperforms existing spiking neural network (SNN) approaches—achieving higher prediction accuracy, superior robustness, and notably stable performance under missing-data conditions.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Time-Series/Data Streams
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Large language models for search
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Spiking Neural Networks (SNNs) offer a promising, biologically inspired approach for processing spatiotemporal data, particularly for time series forecasting. However, conventional neuron models like the Leaky Integrate-and-Fire (LIF) struggle to capture long-term dependencies and effectively process multi-scale temporal dynamics. To overcome these limitations, we introduce the Temporal Segment Leaky Integrate-and-Fire (TS-LIF) model, featuring a novel dual-compartment architecture. The dendritic and somatic compartments specialize in capturing distinct frequency components, providing functional heterogeneity that enhances the neuron's ability to process both low- and high-frequency information. Furthermore, the newly introduced direct somatic current injection reduces information loss during intra-neuronal transmission, while dendritic spike generation improves multi-scale information extraction. We provide a theoretical stability analysis of the TS-LIF model and explain how each compartment contributes to distinct frequency response characteristics. Experimental results show that TS-LIF outperforms traditional SNNs in time series forecasting, demonstrating better accuracy and robustness, even with missing data. TS-LIF advances the application of SNNs in time-series forecasting, providing a biologically inspired approach that captures complex temporal dynamics and offers potential for practical implementation in diverse forecasting scenarios. The source code is available at https://github.com/kkking-kk/TS-LIF.

Problem

• Overcome limitations of traditional SNNs in time series forecasting.
• Enhance multi-scale temporal dynamics processing in spiking neural networks.
• Improve accuracy and robustness in forecasting with missing data.

Innovation

• Dual-compartment architecture enhances temporal dynamics processing
• Direct somatic current injection reduces information loss
• Dendritic spike generation improves multi-scale information extraction