{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/fedali-personalized-federated-learning-with","title":"FedAli: Personalized Federated Learning with Aligned Prototypes through Optimal Transport","arxiv_id":"2411.10595","date":"2024-11-15","proceeding":null,"authors":["Sannara Ek","Kaile Wang","François Portet","Philippe Lalanda","Jiannong Cao"],"abstract":"Federated Learning (FL) enables collaborative, personalized model training across multiple devices without sharing raw data, making it ideal for pervasive computing applications that optimize user-centric performances in diverse environments. However, data heterogeneity among clients poses a significant challenge, leading to inconsistencies among trained client models and reduced performance. To address this, we introduce the Alignment with Prototypes (ALP) layers, which align incoming embeddings closer to learnable prototypes through an optimal transport plan. During local training, the ALP layer updates local prototypes and aligns embeddings toward global prototypes aggregated from all clients using our novel FL framework, Federated Alignment (FedAli). For model inferences, embeddings are guided toward local prototypes to better reflect the client's local data distribution. We evaluate FedAli on heterogeneous sensor-based human activity recognition and vision benchmark datasets, demonstrating that it outperforms existing FL strategies. We publicly release our source code to facilitate reproducibility and furthered research.","url_abs":"https://arxiv.org/abs/2411.10595v1","url_pdf":"https://arxiv.org/pdf/2411.10595v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"fedali-personalized-federated-learning-with","repo_url":"https://github.com/getalp/FedAli","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"activity-recognition","task_name":"Activity Recognition"},{"task_slug":"federated-learning","task_name":"Federated Learning"},{"task_slug":"human-activity-recognition","task_name":"Human Activity Recognition"},{"task_slug":"personalized-federated-learning","task_name":"Personalized Federated Learning"}],"methods":[{"method_slug":"align","method_name":"ALIGN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2411.10595","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}