Global Federated Learning Strategies for Building Efficient Personalized Models

[2608.15107] Global Federated Learning Strategies for Building Efficient Personalized Models Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Machine Learning arXiv:2608.15107 (cs) [Submitted on 15 Aug 2026] Title: Global Federated Learning Strategies for Building Efficient Personalized Models Authors: Seongyoon Kim View a PDF of the paper titled Global Federated Learning Strategies for Building Efficient Personalized Models, by Seongyoon Kim View PDF HTML (experimental) Abstract: Federated learning (FL) is a practical framework that can train models on distributed user data while guaranteeing data privacy; however, due to heterogeneity in which each user has a different data distribution, problems frequently arise where both global and personalization performance deteriorate simultaneously. This dissertation presents methodologies for building efficient personalized models by identifying which strategies are effective in the global training stage and by showing how to preserve global knowledge while securing user-specific performance during local adaptation. First, we show that as data heterogeneity increases, the collapse of feature vectors is a more fundamental bottleneck than classifier weights, and propose a method that directly mitigates the discrepancy in representation magnitude between local and global models. Second, we analyze that a training approach that strengthens local alignment can induce forgetting of global knowledge (e.g., categories not observed locally), and propose a method that achieves both local alignment and global knowledge preservation by combining feature distillation based on the global model's feature vectors. Third, in federated personalized reward model learning with preference heterogeneity, we empirically verify the conventional belief that "increasing the number of global models yields better initialization," and we show that when sufficient local fine-tuning is allowed, a single global initialization can instead provide stronger personalization performance. This study redefines the role of global initialization under data and preference heterogeneity and provides practical training strategies that simultaneously satisfy global knowledge preservation and personalization. Comments: Ph.D. dissertation, Korea Advanced Institute of Science and Technology (KAIST), February 2026 Subjects: Machine Learning (cs.LG) Cite as: arXiv:2608.15107 [cs.LG] (or arXiv:2608.15107v1 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2608.15107 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Seongyoon Kim [ view email ] [v1] Sat, 15 Aug 2026 08:12:52 UTC (2,835 KB) Full-text links: Access Paper: View a PDF of the paper titled Global Federated Learning Strategies for Building Efficient Personalized Models, by Seongyoon Kim View PDF HTML (experimental) TeX Source view license Current browse context: cs.LG < prev | next > new | recent | 2026-08 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: 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? ) IArxiv recommender toggle IArxiv Recommender ( What is IArxiv? ) 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) Major funding support from

Related documents

• Global Federated Learning Strategies for Building Efficient Personalized Models#611057
• Similarity-Aware Personalized Federated Learning in Heterogeneous Environments#822631
• When More Parameters Hurt: Foundation Model Priors Amplify Worst-Client Disparity Under Extreme Federated Heterogeneity#1048649
• Could Model Partitioning Make Federated Learning More Sustainable?#458254
• From Task Mixtures to Specialized Experts#1155515