{"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/heterofl-computation-and-communication-1","title":"HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients","arxiv_id":"2010.01264","date":"2020-10-03","proceeding":"ICLR 2021 1","authors":["Enmao Diao","Jie Ding","Vahid Tarokh"],"abstract":"Federated Learning (FL) is a method of training machine learning models on private data distributed over a large number of possibly heterogeneous clients such as mobile phones and IoT devices. In this work, we propose a new federated learning framework named HeteroFL to address heterogeneous clients equipped with very different computation and communication capabilities. Our solution can enable the training of heterogeneous local models with varying computation complexities and still produce a single global inference model. For the first time, our method challenges the underlying assumption of existing work that local models have to share the same architecture as the global model. We demonstrate several strategies to enhance FL training and conduct extensive empirical evaluations, including five computation complexity levels of three model architecture on three datasets. We show that adaptively distributing subnetworks according to clients' capabilities is both computation and communication efficient.","url_abs":"https://arxiv.org/abs/2010.01264v3","url_pdf":"https://arxiv.org/pdf/2010.01264v3.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":"heterofl-computation-and-communication-1","repo_url":"https://github.com/diaoenmao/HeteroFL-Computation-and-Communication-Efficient-Federated-Learning-for-Heterogeneous-Clients","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"heterofl-computation-and-communication-1","repo_url":"https://github.com/k1l1/SLT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"heterofl-computation-and-communication-1","repo_url":"https://github.com/adap/flower","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"federated-learning","task_name":"Federated Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2010.01264","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.01264"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/k1l1/SLT","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/adap/flower","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/diaoenmao/HeteroFL-Computation-and-Communication-Efficient-Federated-Learning-for-Heterogeneous-Clients","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"ran_draft_wrong":1,"unverified":11},"by_repo_kind":{"official":{"samples":7,"ran":1,"repositories":1},"listed":{"samples":6,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"8af1ed3160ceca12","entry":"FedAvgDevice","repo":"k1l1/SLT","repo_kind":"listed","path":"algorithms/heterofl.py","file_url":"https://github.com/k1l1/SLT/blob/HEAD/algorithms/heterofl.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8af1ed3160ceca12"}},{"code_sha256_prefix":"6fd4f7ea4a79121e","entry":"input_collate","repo":"diaoenmao/HeteroFL-Computation-and-Communication-Efficient-Federated-Learning-for-Heterogeneous-Clients","repo_kind":"official","path":"src/data.py","file_url":"https://github.com/diaoenmao/HeteroFL-Computation-and-Communication-Efficient-Federated-Learning-for-Heterogeneous-Clients/blob/HEAD/src/data.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6fd4f7ea4a79121e"}},{"code_sha256_prefix":"080430395c9cf070","entry":"FedAvgEvaluation","repo":"k1l1/SLT","repo_kind":"listed","path":"algorithms/heterofl.py","file_url":"https://github.com/k1l1/SLT/blob/HEAD/algorithms/heterofl.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"080430395c9cf070"}},{"code_sha256_prefix":"e89d03990ff4aa9c","entry":"FedAvgServer","repo":"k1l1/SLT","repo_kind":"listed","path":"algorithms/heterofl.py","file_url":"https://github.com/k1l1/SLT/blob/HEAD/algorithms/heterofl.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e89d03990ff4aa9c"}},{"code_sha256_prefix":"ebcd0f36349906e5","entry":"FederatedDropoutServer","repo":"k1l1/SLT","repo_kind":"listed","path":"algorithms/heterofl.py","file_url":"https://github.com/k1l1/SLT/blob/HEAD/algorithms/heterofl.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ebcd0f36349906e5"}},{"code_sha256_prefix":"78ba575006dae527","entry":"HeteroFLServer","repo":"k1l1/SLT","repo_kind":"listed","path":"algorithms/heterofl.py","file_url":"https://github.com/k1l1/SLT/blob/HEAD/algorithms/heterofl.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"78ba575006dae527"}},{"code_sha256_prefix":"2d7838d7550bb2fa","entry":"SubsetDevice","repo":"k1l1/SLT","repo_kind":"listed","path":"algorithms/heterofl.py","file_url":"https://github.com/k1l1/SLT/blob/HEAD/algorithms/heterofl.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2d7838d7550bb2fa"}},{"code_sha256_prefix":"e54e85886591c7b5","entry":"check_exists","repo":"diaoenmao/HeteroFL-Computation-and-Communication-Efficient-Federated-Learning-for-Heterogeneous-Clients","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/diaoenmao/HeteroFL-Computation-and-Communication-Efficient-Federated-Learning-for-Heterogeneous-Clients/blob/HEAD/src/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e54e85886591c7b5"}},{"code_sha256_prefix":"750cad056c7e60fd","entry":"fetch_dataset","repo":"diaoenmao/HeteroFL-Computation-and-Communication-Efficient-Federated-Learning-for-Heterogeneous-Clients","repo_kind":"official","path":"src/data.py","file_url":"https://github.com/diaoenmao/HeteroFL-Computation-and-Communication-Efficient-Federated-Learning-for-Heterogeneous-Clients/blob/HEAD/src/data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"750cad056c7e60fd"}},{"code_sha256_prefix":"eb70b22d55cbf5cb","entry":"load","repo":"diaoenmao/HeteroFL-Computation-and-Communication-Efficient-Federated-Learning-for-Heterogeneous-Clients","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/diaoenmao/HeteroFL-Computation-and-Communication-Efficient-Federated-Learning-for-Heterogeneous-Clients/blob/HEAD/src/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"eb70b22d55cbf5cb"}},{"code_sha256_prefix":"d953f71ff87c935d","entry":"make_flops","repo":"diaoenmao/HeteroFL-Computation-and-Communication-Efficient-Federated-Learning-for-Heterogeneous-Clients","repo_kind":"official","path":"src/summary.py","file_url":"https://github.com/diaoenmao/HeteroFL-Computation-and-Communication-Efficient-Federated-Learning-for-Heterogeneous-Clients/blob/HEAD/src/summary.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d953f71ff87c935d"}},{"code_sha256_prefix":"8d994cf212a4e904","entry":"make_size","repo":"diaoenmao/HeteroFL-Computation-and-Communication-Efficient-Federated-Learning-for-Heterogeneous-Clients","repo_kind":"official","path":"src/summary.py","file_url":"https://github.com/diaoenmao/HeteroFL-Computation-and-Communication-Efficient-Federated-Learning-for-Heterogeneous-Clients/blob/HEAD/src/summary.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8d994cf212a4e904"}},{"code_sha256_prefix":"ee167d57eabab823","entry":"to_device","repo":"diaoenmao/HeteroFL-Computation-and-Communication-Efficient-Federated-Learning-for-Heterogeneous-Clients","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/diaoenmao/HeteroFL-Computation-and-Communication-Efficient-Federated-Learning-for-Heterogeneous-Clients/blob/HEAD/src/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ee167d57eabab823"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}