Metraipolis › archive › dc_b5483206589a

Similarity-Aware Personalized Federated Learning in Heterogeneous Environments — arXiv:2609.02241

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.02241
License (as archived)
CC0-1.0
Archived
2026-10-17T04:59:27.859Z
SHA-256 of the archived text
c0ab390b4a49019e5835063e7bdf30ed1a65f53543fd309c9b648d08a1c1424c
Stable URL of this page
https://metraipolis.com/documento/dc_b5483206589a

How to cite

Similarity-Aware Personalized Federated Learning in Heterogeneous Environments — arXiv:2609.02241 — arXiv (en), https://arxiv.org/abs/2609.02241 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b5483206589a (Metraipolis archive dc_b5483206589a, sha256 c0ab390b4a49019e5835063e7bdf30ed1a65f53543fd309c9b648d08a1c1424c)
BibTeX
@misc{dcb5483206589a,
  title = {Similarity-Aware Personalized Federated Learning in Heterogeneous Environments — arXiv:2609.02241},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.02241},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b5483206589a; sha256 c0ab390b4a49019e5835063e7bdf30ed1a65f53543fd309c9b648d08a1c1424c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02241. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-03 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.02241 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T04:09:43.319Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).