TIM: An Efficient Temporal Interaction Module for Spiking Transformer

TL;DR

This paper introduces TIM, a convolution-based module that enhances the temporal processing capabilities of Spiking Neural Networks, leading to improved performance on neuromorphic datasets with minimal additional parameters.

Contribution

The paper proposes TIM, a novel temporal interaction module that seamlessly integrates into SNNs to significantly improve their temporal data processing abilities.

Findings

TIM achieves state-of-the-art results on neuromorphic datasets.

TIM enhances the temporal information handling with minimal parameter increase.

Experimental results validate TIM's effectiveness in SNNs.

Abstract

Spiking Neural Networks (SNNs), as the third generation of neural networks, have gained prominence for their biological plausibility and computational efficiency, especially in processing diverse datasets. The integration of attention mechanisms, inspired by advancements in neural network architectures, has led to the development of Spiking Transformers. These have shown promise in enhancing SNNs' capabilities, particularly in the realms of both static and neuromorphic datasets. Despite their progress, a discernible gap exists in these systems, specifically in the Spiking Self Attention (SSA) mechanism's effectiveness in leveraging the temporal processing potential of SNNs. To address this, we introduce the Temporal Interaction Module (TIM), a novel, convolution-based enhancement designed to augment the temporal data processing abilities within SNN architectures. TIM's integration into existing SNN frameworks is seamless and efficient, requiring minimal additional parameters while significantly boosting their temporal information handling capabilities. Through rigorous experimentation, TIM has demonstrated its effectiveness in exploiting temporal information, leading to state-of-the-art performance across various neuromorphic datasets. The code is available at https://github.com/BrainCog-X/Brain-Cog/tree/main/examples/TIM.