# FedPAE: Peer-Adaptive Ensemble Learning for Asynchronous and Model-Heterogeneous Federated Learning Source: [FedPAE: Peer-Adaptive Ensemble Learning for Asynchronous and Model-Heterogeneous Federated Learning]() Collection index: [llms.txt]() Data updated: 2025-10-26T03:30:07.152Z Authors: Brianna Mueller, W. Nick Street, Stephen Baek, Qihang Lin, Jingyi Yang, Yankun Huang Published: 2024-10-17T22:47:19.000Z ## Abstract Federated learning (FL) enables multiple clients with distributed data sources to collaboratively train a shared model without compromising data privacy. However, existing FL paradigms face challenges due to heterogeneity in client data distributions and system capabilities. Personalized federated learning (pFL) has been proposed to mitigate these problems, but often requires a shared model architecture and a central entity for parameter aggregation, resulting in scalability and communication issues. More recently, model-heterogeneous FL has gained attention due to its ability to support diverse client models, but existing methods are limited by their dependence on a centralized framework, synchronized training, and publicly available datasets. To address these limitations, we introduce Federated Peer-Adaptive Ensemble Learning (FedPAE), a fully decentralized pFL algorithm that supports model heterogeneity and asynchronous learning. Our approach utilizes a peer-to-peer model sharing mechanism and ensemble selection to achieve a more refined balance between local and global information. Experimental results show that FedPAE outperforms existing state-of-the-art pFL algorithms, effectively managing diverse client capabilities and demonstrating robustness against statistical heterogeneity. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Image Classification on EuroSAT geographic (50 regions) (test)](): Image Classification; EuroSAT geographic (50 regions) (test); Accuracy: 94.8. - [Image Classification on CIFAR-100 (test) (Accuracy and Throughput)](): Image Classification; CIFAR-100 (test); Accuracy: 54.9. - [Image Classification on CIFAR-10 (test) (Accuracy and Sparsity)](): Image Classification; CIFAR-10 (test); Accuracy: 78. - [Image Classification on CIFAR-10 (Accuracy)](): Image Classification; CIFAR-10; Accuracy: 78. ## Original sources and implementation [Original paper]() [PDF]()