{"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/fedproto-federated-prototype-learning-over","title":"FedProto: Federated Prototype Learning across Heterogeneous Clients","arxiv_id":"2105.00243","date":"2021-05-01","proceeding":null,"authors":["Yue Tan","Guodong Long","Lu Liu","Tianyi Zhou","Qinghua Lu","Jing Jiang","Chengqi Zhang"],"abstract":"Heterogeneity across clients in federated learning (FL) usually hinders the optimization convergence and generalization performance when the aggregation of clients' knowledge occurs in the gradient space. For example, clients may differ in terms of data distribution, network latency, input/output space, and/or model architecture, which can easily lead to the misalignment of their local gradients. To improve the tolerance to heterogeneity, we propose a novel federated prototype learning (FedProto) framework in which the clients and server communicate the abstract class prototypes instead of the gradients. FedProto aggregates the local prototypes collected from different clients, and then sends the global prototypes back to all clients to regularize the training of local models. The training on each client aims to minimize the classification error on the local data while keeping the resulting local prototypes sufficiently close to the corresponding global ones. Moreover, we provide a theoretical analysis to the convergence rate of FedProto under non-convex objectives. In experiments, we propose a benchmark setting tailored for heterogeneous FL, with FedProto outperforming several recent FL approaches on multiple datasets.","url_abs":"https://arxiv.org/abs/2105.00243v4","url_pdf":"https://arxiv.org/pdf/2105.00243v4.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":"fedproto-federated-prototype-learning-over","repo_url":"https://github.com/yuetan031/fedproto","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"fedproto-federated-prototype-learning-over","repo_url":"https://github.com/KarhouTam/FL-bench","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"fedproto-federated-prototype-learning-over","repo_url":"https://github.com/TsingZ0/PFL-Non-IID","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"fedproto-federated-prototype-learning-over","repo_url":"https://github.com/TsingZ0/GFL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"federated-learning","task_name":"Federated Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2105.00243","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}