Binary Event-Driven Spiking Transformer
This work addresses the challenge of deploying high-performance AI models on resource-limited edge devices, representing an incremental improvement through the integration of binarization techniques into existing SNN-Transformer hybrids.
The paper tackles the problem of high computational demands in Transformer-based Spiking Neural Networks (SNNs) by proposing BESTformer, a binary event-driven spiking transformer that reduces storage and computation using 1-bit representations, achieving superior performance to other binary SNNs on static and neuromorphic datasets.
Transformer-based Spiking Neural Networks (SNNs) introduce a novel event-driven self-attention paradigm that combines the high performance of Transformers with the energy efficiency of SNNs. However, the larger model size and increased computational demands of the Transformer structure limit their practicality in resource-constrained scenarios. In this paper, we integrate binarization techniques into Transformer-based SNNs and propose the Binary Event-Driven Spiking Transformer, i.e. BESTformer. The proposed BESTformer can significantly reduce storage and computational demands by representing weights and attention maps with a mere 1-bit. However, BESTformer suffers from a severe performance drop from its full-precision counterpart due to the limited representation capability of binarization. To address this issue, we propose a Coupled Information Enhancement (CIE) method, which consists of a reversible framework and information enhancement distillation. By maximizing the mutual information between the binary model and its full-precision counterpart, the CIE method effectively mitigates the performance degradation of the BESTformer. Extensive experiments on static and neuromorphic datasets demonstrate that our method achieves superior performance to other binary SNNs, showcasing its potential as a compact yet high-performance model for resource-limited edge devices.