FedLBW: A Loss-Based Weighting Strategy for Federated Learning on Non-IID Data in Wireless Networks
Summary
This paper proposes FedLBW, a federated learning aggregation strategy that weights client updates by inverse validation loss instead of dataset size, improving accuracy and robustness to non-IID data and client dropouts in wireless networks.
View Cached Full Text
Cached at: 08/10/26, 08:00 AM
# FedLBW: A Loss-Based Weighting Strategy for Federated Learning on Non-IID Data in Wireless Networks Source: [https://arxiv.org/abs/2608.07007](https://arxiv.org/abs/2608.07007) [View PDF](https://arxiv.org/pdf/2608.07007) > Abstract: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\. ## Submission history From: Taehong Kim \[[view email](https://arxiv.org/show-email/bfe83162/2608.07007)\] **\[v1\]**Fri, 7 Aug 2026 09:21:37 UTC \(730 KB\)
Similar Articles
On the Push-Based Asynchronous Federated Learning: A Bias-Correction Aggregation Approach
This paper presents PushCen-ADFL, a communication-efficient asynchronous decentralized federated learning framework that uses centroid-based messaging and bias-correction to improve accuracy and reduce communication overhead under heterogeneous conditions.
Federated Lightweight Fine-Tuning
This paper introduces FLITE (Federated Low-rank Iterative Training Engine), a method for federated fine-tuning that reduces per-client communication to 1,280 floats per round (about 5KB) — an 8718× reduction over full-weight FedAvg — by using a frozen affine mapping network that generates weights from a small trainable latent and a low-rank seed-regenerable factorization, achieving accuracy within 0.5 percentage points of full-weight FedAvg on CIFAR-100 with ResNet-18.
A Comparative Study of Federated Learning Aggregation Strategies under Homogeneous and Heterogeneous Data Distributions
This paper presents a comprehensive experimental comparison of various federated learning aggregation strategies, analyzing their performance and efficiency under both homogeneous and heterogeneous data distributions.
FIRMA: FIbonacci Ring Model Aggregation for Privacy-preserving Federated Learning
This paper introduces FIRMA, a family of three privacy-preserving federated learning protocols using Fibonacci-weighted ring aggregation to achieve server-free operation, permanently private classification heads, and improved accuracy under data heterogeneity.
Robust Federated Learning Under Real-World Client Churn
FeLiX is a new federated learning orchestration framework that optimizes time-to-target accuracy on live interaction streams by handling transient client availability, dynamic data heterogeneity, and outcome delays. It introduces streaming-aware availability tiers, fresh-utility selection, and delay-robust aggregation, reducing wall-clock time by up to 2.37x and communication bandwidth by 1.30x versus state-of-the-art baselines.