Convolutional Spiking-based GRU Cell for Spatio-temporal Data

2025-10-29

AI Summary

To address the challenge of modeling fine-grained local spatiotemporal dependencies in event-driven time-series data, this paper proposes the Convolutional Spiking Gated Recurrent Unit (CS-GRU)—the first architecture to integrate convolutional operations into a spiking GRU framework. CS-GRU synergistically combines the temporal precision of spiking neural networks, the gated dynamics of GRUs, and the spatial locality awareness of convolutions, explicitly capturing local spatiotemporal structure while preserving event sparsity and temporal sensitivity. Evaluated on benchmark datasets—including NTIDIGITS, DVSGesture, and MNIST—CS-GRU achieves an average accuracy improvement of 4.35% over existing GRU variants; notably, it attains 99.31% accuracy on MNIST. Moreover, its inference efficiency surpasses that of SpikGRU by 69%. Thus, CS-GRU delivers a co-optimized balance of high accuracy and computational efficiency for event-based sequence modeling.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Learning on the Edge & Model Compression

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: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Models for Web evolution

Abstract

Spike-based temporal messaging enables SNNs to efficiently process both purely temporal and spatio-temporal time-series or event-driven data. Combining SNNs with Gated Recurrent Units (GRUs), a variant of recurrent neural networks, gives rise to a robust framework for sequential data processing; however, traditional RNNs often lose local details when handling long sequences. Previous approaches, such as SpikGRU, fail to capture fine-grained local dependencies in event-based spatio-temporal data. In this paper, we introduce the Convolutional Spiking GRU (CS-GRU) cell, which leverages convolutional operations to preserve local structure and dependencies while integrating the temporal precision of spiking neurons with the efficient gating mechanisms of GRUs. This versatile architecture excels on both temporal datasets (NTIDIGITS, SHD) and spatio-temporal benchmarks (MNIST, DVSGesture, CIFAR10DVS). Our experiments show that CS-GRU outperforms state-of-the-art GRU variants by an average of 4.35%, achieving over 90% accuracy on sequential tasks and up to 99.31% on MNIST. It is worth noting that our solution achieves 69% higher efficiency compared to SpikGRU. The code is available at: https://github.com/YesmineAbdennadher/CS-GRU.

Problem

• Capturing fine-grained local dependencies in spatio-temporal data
• Preserving local structure while processing long sequential data
• Improving efficiency and accuracy for event-driven data processing

Innovation

• Convolutional Spiking GRU cell preserves local dependencies
• Integrates spiking neurons with GRU gating mechanisms
• Achieves higher accuracy and efficiency on benchmarks