aiqbench analysis
This paper introduces SAPE-FL, a federated learning framework designed to handle statistical heterogeneity by anchoring local models to both global and similarity-weighted peer averages. The approach theoretically guarantees convergence while empirically demonstrating superior robustness in low-data regimes where standard collaborative methods fail. By dynamically filtering out dissimilar clients, it effectively mitigates negative transfer without compromising data privacy.
Similarity-Aware Personalized Federated Learning in Heterogeneous Environments
arXiv:2609.02241v1 Announce Type: new Abstract: Federated Learning (FL) allows decentralized clients to train models collaboratively while preserving data privacy. However, distribution mismatch across clients often leads to poor global generalization and degraded local client-level performance. In such scenarios, some of the clients with their local models trained solely on local data may perform better than the globally learnt model, thus nullifying the benefits of collaborative federated learning. To address this, we propose SAPE-FL (Similarity-Aware Personalized Federated Learning), a novel personalization framework that anchors each client's model to both the global model and a similarity-weighted peer averaged model. By incorporating dynamic, client-specific regularization based on both model similarity and output similarity, SAPE-FL adaptively balances global knowledge transfer and peer collaboration while filtering out dissimilar clients. This dual anchoring mitigates negative transfer and enhances robustness in heterogeneous settings. We theoretically analyze our algorithm establishing its convergence guarantees and empirically show that SAPE-FL outperforms state-of-the-art methods under high statistical heterogeneity and low client data regimes.
Abstract:Federated Learning (FL) allows decentralized clients to train models collaboratively while preserving data privacy. However, distribution mismatch across clients often leads to poor global generalization and degraded local client-level performance. In such scenarios, some of the clients with their local models trained solely on local data may perform better than the globally learnt model, thus nullifying the benefits of collaborative federated learning. To address this, we propose SAPE-FL (Similarity-Aware Personalized Federated Learning), a novel personalization framework that anchors each client's model to both the global model and a similarity-weighted peer averaged model. By incorporating dynamic, client-specific regularization based on both model similarity and output similarity, SAPE-FL adaptively balances global knowledge transfer and peer collaboration while filtering out dissimilar clients. This dual anchoring mitigates negative transfer and enhances robustness in heterogeneous settings. We theoretically analyze our algorithm establishing its convergence guarantees and empirically show that SAPE-FL outperforms state-of-the-art methods under high statistical heterogeneity and low client data regimes.
Machine Learning (cs.LG)
arXiv:2609.02241 [cs.LG]
(or arXiv:2609.02241v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.02241 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 251 words
Related coverage
Digital States 2026: AI Moves From Experiment to Infrastructure
govtech.com · Sep 24, 2026
AlignFed: Alignment-Aware Asynchronous Federated Fine-Tuning for Large Language Models in Heterogeneous Edge Environments
arXiv · Jun 9, 2026
FedCKA: Representation-Guided Layer Personalization for Federated 3D Perception Across Driving Domains
arXiv · Oct 2, 2026
CF-LoRA: Decoupled Factor Aggregation and Adaptation-Aware Client Clustering for Federated LoRA Fine-Tuning
arXiv · Sep 30, 2026