SFedHIFI: Fire Rate-Based Heterogeneous Information Fusion for Spiking Federated Learning

2026-03-16

AI Summary

Existing spiking federated learning approaches are constrained by assumptions of model homogeneity and high computational demands, hindering their deployment on resource-heterogeneous edge devices. This work proposes the first federated learning framework enabling collaborative training of heterogeneous-width spiking neural networks (SNNs). The method employs channel-wise matrix decomposition to adapt to diverse client-side resource constraints and introduces a firing-rate-driven mechanism for cross-scale knowledge fusion and aggregation. By decoupling the reliance on structural model consistency inherent in conventional federated learning, the approach achieves accuracy comparable to homogeneous methods on three public datasets while significantly outperforming existing baselines. Moreover, it substantially reduces energy consumption compared to artificial neural network (ANN)-based federated schemes.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Search and Optimization: Learning to Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

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.

Problem

• Spiking Federated Learning
• model heterogeneity
• resource-constrained clients
• system heterogeneity
• heterogeneous information fusion

Innovation

• Spiking Federated Learning
• Model Heterogeneity
• Fire Rate-Based Fusion
• Channel-wise Matrix Decomposition
• Energy Efficiency