摘要： 联邦学习作为一种分布式边缘训练框架，无需集中客户端私有数据的前提下完成模型训练，因而在数据隐私与安全性方面具有显著优势。然而在实际应用中，客户端之间不仅面临通信受限的问题，更普遍存在由于数据分布不一致（非独立同分布，Non-IID）所带来的性能退化问题。针对这一挑战，本文提出一种多流特征感知网络FedMFP。具体而言，该方法通过设计双流特征分离架构，分别提取客户端的全局流和细粒度流特征：全局流网络利用特征扰动器(Feature Perturber)/特征补偿器(Feature Compensator)机制捕捉样本间整体相关性；细粒度流网络则采用多流架构提取多尺度个性化信息；同时，通过设计不同的损失函数对这两类特征进行有效解耦，最大限度降低特征间的相互干扰。大量实验结果表明，FedMFP在Cifar100、Tiny-ImageNet等经典非独立同分布数据集上，测试准确率相比对比的九种算法分别平均提高了13.27%、14.41%，显著提升了模型在Non-IID数据下的泛化能力与鲁棒性。

Abstract: Federated Learning (FL), as a distributed edge training framework, enables model training without centralizing clients' private data, thus offering significant advantages in terms of data privacy and security. However, in practical applications, clients not only face communication constraints but, more commonly, suffer from performance degradation due to inconsistent data distributions (Non-Independent and Identically Distributed, Non-IID). To address this challenge, this paper proposes a Multi-stream Feature-aware Network, FedMFP. Specifically, the method employs a dual-stream feature decoupling architecture to separately extract global features and fine-grained features from clients: The global stream network utilizes feature perturber/ compensator mechanisms to capture inter-sample correlations from a holistic perspective; The fine-grained stream network adopts a multi-stream architecture to extract personalized multi-scale information. Concurrently, distinct loss functions are designed to effectively decouple these two types of features, minimizing mutual interference between them. Extensive experimental results demonstrate that FedMFP achieves average test accuracy improvements of 13.27% and 14.41% compared to nine baseline algorithms on classic Non-IID datasets including Cifar100 and Tiny-ImageNet, significantly enhancing the model's generalization capability and robustness under Non-IID data distributions.