SFedHIFI: Fire Rate-Based Heterogeneous Information Fusion for Spiking Federated Learning
This work addresses the exclusion of resource-constrained clients in SFL, enabling more inclusive and efficient federated learning systems in real-world scenarios.
The paper tackled the problem of system heterogeneity in Spiking Federated Learning (SFL) by proposing SFedHIFI, a framework that allows clients to deploy models of different scales based on local resources, resulting in consistent outperformance over three baseline methods and significant energy savings compared to ANN-based FL with only a marginal accuracy trade-off.
Spiking Federated Learning (SFL) has been widely studied with the energy efficiency of Spiking Neural Networks (SNNs). However, existing SFL methods require model homogeneity and assume all clients have sufficient computational resources, resulting in the exclusion of some resource-constrained clients. To address the prevalent system heterogeneity in real-world scenarios, enabling heterogeneous SFL systems that allow clients to adaptively deploy models of different scales based on their local resources is crucial. To this end, we introduce SFedHIFI, a novel Spiking Federated Learning framework with Fire Rate-Based Heterogeneous Information Fusion. Specifically, SFedHIFI employs channel-wise matrix decomposition to deploy SNN models of adaptive complexity on clients with heterogeneous resources. Building on this, the proposed heterogeneous information fusion module enables cross-scale aggregation among models of different widths, thereby enhancing the utilization of diverse local knowledge. Extensive experiments on three public benchmarks demonstrate that SFedHIFI can effectively enable heterogeneous SFL, consistently outperforming all three baseline methods. Compared with ANN-based FL, it achieves significant energy savings with only a marginal trade-off in accuracy.