AS-FedBridge: Pseudo-Spike Bridge Distillation for Heterogeneous ANN-SNN Federated Learning

2026-08-04

AI Summary

This work addresses the representational misalignment between artificial neural networks (ANNs) and spiking neural networks (SNNs) in federated learning, which arises from their fundamentally different information representations and hinders collaborative training across heterogeneous models. To bridge this gap, the authors propose AS-FedBridge, the first federated learning framework supporting mixed ANN–SNN clients. It introduces a lightweight pseudo-spiking bridging module that maps continuous ANN activations into an SNN-compatible spiking space, coupled with bridge distillation and cross-modal representation alignment techniques. This approach achieves effective representation alignment and a favorable trade-off between performance and efficiency with negligible computational overhead. Extensive experiments across four datasets demonstrate significant accuracy improvements, robustness under extreme heterogeneity in scale and architecture, and establish the first benchmark for ANN–SNN hybrid federated learning.

Abstract

Federated learning enables collaborative model training across distributed edge devices while strictly preserving data privacy. To facilitate practical deployment on resource-constrained edge devices, Spiking Neural Networks (SNNs) have emerged as a promising alternative to traditional Artificial Neural Networks (ANNs) due to their sparse computing mechanisms and high energy efficiency. However, jointly training ANNs and SNNs exposes a challenge of representational misalignment, which is intrinsically caused by differences in information representation, specifically the semantic gap between continuous real-valued activations in ANNs and discrete spatio-temporal spikes in SNNs. To overcome this barrier, we propose AS-FedBridge, a novel federated learning framework tailored for mixed ANN-SNN clients. AS-FedBridge features a lightweight Bridge equipped with a Pseudo-Spike Interface, which effectively projects continuous signals into a spike-compatible space to facilitate ANN-SNN alignment. Given the absence of existing mixed ANN-SNN federated frameworks, we establish a comprehensive benchmark to evaluate against multiple advanced heterogeneous FL methods. Our empirical analysis demonstrates a positive correlation between the degree of ANN-SNN alignment and the collaborative FL performance. Across four datasets, AS-FedBridge consistently demonstrates advanced accuracy while mitigating extreme scale, architecture, and client heterogeneity challenge. Furthermore, our framework enables a highly controllable trade-off between model performance and resource efficiency. AS-FedBridge accomplishes these robust performance gains while introducing only marginal computational overhead, establishing a robust and practical foundation for mixed ANN-SNN federated learning systems.

Problem

• Federated Learning
• Spiking Neural Networks
• Artificial Neural Networks
• Heterogeneous Learning
• Representational Misalignment

Innovation

• Federated Learning
• Spiking Neural Networks
• Heterogeneous Learning
• Pseudo-Spike Distillation
• ANN-SNN Alignment