Temporal Reversal Regularization for Spiking Neural Networks: Hybrid Spatio-Temporal Invariance for Generalization

TL;DR

This paper introduces Temporal Reversal Regularization (TRR), a novel method that leverages input and feature reversal perturbations in spiking neural networks to improve generalization, robustness, and accuracy across various tasks.

Contribution

The paper proposes TRR, a simple regularization technique exploiting temporal properties of SNNs, with theoretical and empirical validation for enhanced generalization and robustness.

Findings

TRR improves SNN generalization error bounds.

Experimental results show increased accuracy on recognition and classification tasks.

TRR enhances adversarial robustness and low-latency performance.

Abstract

Spiking neural networks (SNNs) have received widespread attention as an ultra-low power computing paradigm. Recent studies have shown that SNNs suffer from severe overfitting, which limits their generalization performance. In this paper, we propose a simple yet effective Temporal Reversal Regularization (TRR) to mitigate overfitting during training and facilitate generalization of SNNs. We exploit the inherent temporal properties of SNNs to perform input/feature temporal reversal perturbations, prompting the SNN to produce original-reversed consistent outputs and learn perturbation-invariant representations. To further enhance generalization, we utilize the lightweight ``star operation" (Hadamard product) for feature hybridization of original and temporally reversed spike firing rates, which expands the implicit dimensionality and acts as a spatio-temporal regularizer. We show theoretically that our method is able to tighten the upper bound of the generalization error, and extensive experiments on static/neuromorphic recognition as well as 3D point cloud classification tasks demonstrate its effectiveness, versatility, and adversarial robustness. In particular, our regularization significantly improves the recognition accuracy of low-latency SNN for neuromorphic objects, contributing to the real-world deployment of neuromorphic computational software-hardware integration.