FedLBW：面向无线网络中非独立同分布数据的联邦学习的基于损失的加权策略
FedLBW: A Loss-Based Weighting Strategy for Federated Learning on Non-IID Data in Wireless Networks
浏览论文内容
中文总结 AI 辅助
针对无线网络联邦学习面临的非IID数据与客户端弃权问题，本文提出FedLBW算法，以验证损失倒数为权重聚合客户端更新，在多数据集实验中较基线算法实现更高准确率与更快收敛，鲁棒性更强。
中文摘要 AI 辅助
联邦学习（Federated Learning, FL）可在分布式客户端间开展协作式机器学习（Machine Learning, ML），同时保护隐私。但联邦学习的高效模型收敛仍存在挑战，尤其是在无线网络中，非独立同分布（non-IID）数据和频繁的客户端弃权（不执行）十分常见。传统联邦学习算法（如FedAvg）仅依赖数据集大小对客户端更新进行加权，这会偏向拥有更大数据集的客户端，使过程对非IID数据、异常值和客户端弃权（不执行）敏感。为应对这些挑战，本文提出基于损失的加权联邦学习（Federated Learning with Loss-Based Weighting, FedLBW），这是一种新型聚合方法，它为每个客户端的更新分配的权重与服务器上用小型代理数据集计算的验证损失的倒数成正比，而非其数据集大小。这确保低损失模型在聚合过程中发挥更大影响，优先考虑最可靠的更新并提升整体性能。通过在多个数据集上开展的大量实验，包括FashionMNIST（CNN）、CIFAR-10（ResNet-18）和CIFAR-100（ResNet-34），本文证明FedLBW与FedAvg、FedAvgM、FedProx、FedNova、FedLAW和FedDkw等基线算法相比，实现了更高的准确率和更快的收敛速度，在极端非IID情况下，CIFAR-10上的准确率提升最高达7.6%。此外，FedLBW对不断提高的弃权（不执行）概率展现出出色的弹性，即使在具有挑战性的条件下也始终保持显著更高的准确率。这些结果确立了FedLBW作为无线网络环境中联邦学习的有效且具弹性的解决方案，在模型准确率、收敛速度以及对非IID数据和客户端弃权（不执行）的鲁棒性方面提供了显著改进。
英文摘要
Federated Learning (FL) enables collaborative machine learning (ML) across distributed clients while preserving privacy. However, efficient model convergence in FL remains challenging, especially in wireless networks where non-independent and identically distributed (non-IID) data and frequent client dropouts are common. Traditional FL algorithms, such as FedAvg, rely solely on dataset size to weight client updates. This introduces biases towards clients with larger datasets and makes the process sensitive to non-IID data, outliers, and client dropouts. To address these challenges, we propose Federated Learning with Loss-Based Weighting (FedLBW), a novel aggregation method that assigns each client's update a weight proportional to the inverse of its validation loss, computed using a small proxy dataset on the server, rather than its dataset size. This ensures that lower-loss models exert greater influence during aggregation, prioritizing the most reliable updates and boosting overall performance. Through extensive experiments across multiple datasets, including FashionMNIST (CNN), CIFAR-10 (ResNet-18), and CIFAR-100 (ResNet-34), we demonstrate that FedLBW achieves higher accuracy and faster convergence compared to baseline algorithms such as FedAvg, FedAvgM, FedProx, FedNova, FedLAW and FedDkw, with notable improvements of up to 7.6 % higher accuracy on CIFAR-10 in extreme non-IID cases. Moreover, FedLBW showcases exceptional resilience to increasing dropout probabilities, consistently maintaining significantly higher accuracy even in challenging conditions. These results establish FedLBW as an effective and resilient solution for FL in wireless network environments, offering marked improvements in model accuracy, convergence speed, and robustness to non-IID data and client dropouts.
发表机构
- Chungbuk National University（忠北国立大学）
- Bennett University（班尼特大学）
机构由 AI 辅助整理，请以论文原文为准。
