解决边缘设备标签偏斜问题，提升联邦学习中脉冲神经网络性能
Exploiting Label Skewness for Spiking Neural Networks in Federated Learning
- 通过客户端内标签权重校准平衡学习强度
- 采用跨客户端知识蒸馏缓解标签缺失导致的模型偏差
- 在5个数据集上平均提升11.59%准确率，适合资源受限场景
深度脉冲神经网络（SNN）的能效特性契合资源受限边缘设备的需求，是智能应用的理想基础。为保护数据隐私，联邦学习（FL）可在不传输本地数据的前提下实现分布式协同训练。然而现有方法难以应对设备间标签分布偏斜问题，导致局部SNN模型漂移，降低全局模型性能。本文提出新框架FedLEC，引入客户端内标签权重校准以平衡各标签的学习强度，并通过客户端间知识蒸馏缓解因标签缺失引发的模型偏差。在三个结构化SNN与五个数据集（含三个非类脑、两个类脑数据集）上的实验表明，相比八种先进联邦学习算法，FedLEC在多种标签偏斜设置下使全局SNN模型平均准确率提升约11.59%。
原文摘要 · Abstract (English)
The energy efficiency of deep spiking neural networks (SNNs) aligns with the constraints of resource-limited edge devices, positioning SNNs as a promising foundation for intelligent applications leveraging the extensive data collected by these devices. To address data privacy concerns when deploying SNNs on edge devices, federated learning (FL) facilitates collaborative model training by leveraging data distributed across edge devices without transmitting local data to a central server. However, existing FL approaches struggle with label-skewed data across devices, which leads to drift in local SNN models and degrades the performance of the global SNN model. In this paper, we propose a novel framework called FedLEC, which incorporates intra-client label weight calibration to balance the learning intensity across local labels and inter-client knowledge distillation to mitigate local SNN model bias caused by label absence. Extensive experiments with three different structured SNNs across five datasets (i.e., three non-neuromorphic and two neuromorphic datasets) demonstrate the efficiency of FedLEC. Compared to eight state-of-the-art FL algorithms, FedLEC achieves an average accuracy improvement of approximately 11.59% for the global SNN model under various label skew distribution settings.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。