FedPromo: Federated Lightweight Proxy Models at the Edge Bring New Domains to Foundation Models

[2508.03356] FedPromo: Federated Lightweight Proxy Models at the Edge Bring New Domains to Foundation Models Skip to main content Search Submit Donate Log in Computer Science > Computer Vision and Pattern Recognition arXiv:2508.03356 (cs) [Submitted on 5 Aug 2025 ( v1 ), last revised 24 Nov 2025 (this version, v2)] Title: FedPromo: Federated Lightweight Proxy Models at the Edge Bring New Domains to Foundation Models Authors: Matteo Caligiuri , Francesco Barbato , Donald Shenaj , Umberto Michieli , Pietro Zanuttigh View PDF HTML (experimental) Abstract: Federated Learning (FL) is an established paradigm for training deep learning models on decentralized data. However, as the size of the models grows, conventional FL approaches often require significant computational resources on client devices, which may not be feasible. We introduce FedPromo, a novel framework that enables efficient adaptation of large-scale foundation models stored on a central server to new domains encountered only by remote clients. Instead of directly training the large model on client devices, FedPromo optimizes lightweight proxy models via FL, significantly reducing computational overhead while maintaining privacy. Our method follows a two-stage process: first, server-side knowledge distillation aligns the representations of a large-scale foundation model (e.g., a transformer) with those of a compact counterpart (e.g., a CNN). Then, the compact model encoder is deployed to client devices, where trainable classifiers are learned locally. These classifiers are subsequently aggregated and seamlessly transferred back to the foundation model, facilitating personalized adaptation without requiring direct access to user data. Through novel regularization strategies, our framework enables decentralized multi-domain learning, balancing performance, privacy, and resource efficiency. Extensive experiments on five image classification benchmarks demonstrate that FedPromo outperforms existing methods while assuming limited-resource clients. Comments: 8 pages (main document) + 13 pages (suppl. mat.), 4 figures (main) + 11 figures (suppl. mat.), 6 tables (main) + 5 tables (suppl. mat.) + 4 algorithms (suppl. mat.) Subjects: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG) Cite as: arXiv:2508.03356 [cs.CV] (or arXiv:2508.03356v2 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2508.03356 Focus to learn more arXiv-issued DOI via DataCite Journal reference: IEEE Internet of Things Journal 2026 Related DOI : https://doi.org/10.1109/JIOT.2026.3710527 Focus to learn more DOI(s) linking to related resources Submission history From: Francesco Barbato Ph.D. [ view email ] [v1] Tue, 5 Aug 2025 12:00:49 UTC (12,390 KB) [v2] Mon, 24 Nov 2025 15:33:16 UTC (9,374 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.CV < prev | next > new | recent | 2025-08 Change to browse by: cs cs.LG References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators 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 . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab)

Related documents

• FedPromo: Federated Lightweight Proxy Models at the Edge Bring New Domains to Foundation Models#670363
• Preserving Provenance in Shared KV Caches for LLM Serving#1143307
• FedLNS: Leverage LayerNorm Signature Modeling to Mitigate Adversarial Manipulation in Federated LLMs#467079
• A maturity model framework for federated networks of trusted research environments.#242307
• Ensuring Fairness and Gradient Privacy in Personalized Heterogeneous Federated Learning#303020