Search papers, labs, and topics across Lattice.
This paper introduces SAPE-FL, a novel framework for personalized federated learning that addresses the challenges of distribution mismatch among clients by anchoring each client's model to both a global model and a similarity-weighted peer averaged model. By implementing dynamic, client-specific regularization based on model and output similarity, SAPE-FL effectively balances global knowledge transfer with peer collaboration, filtering out dissimilar clients to mitigate negative transfer. Empirical results demonstrate that SAPE-FL significantly outperforms existing state-of-the-art methods in scenarios characterized by high statistical heterogeneity and limited client data.
SAPE-FL achieves superior model performance in heterogeneous environments by intelligently balancing global and local learning through similarity-aware personalization.
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.
