{"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/where-to-begin-exploring-the-impact-of-pre","title":"Where to Begin? On the Impact of Pre-Training and Initialization in Federated Learning","arxiv_id":"2206.15387","date":"2022-06-30","proceeding":null,"authors":["John Nguyen","Jianyu Wang","Kshitiz Malik","Maziar Sanjabi","Michael Rabbat"],"abstract":"An oft-cited challenge of federated learning is the presence of heterogeneity. \\emph{Data heterogeneity} refers to the fact that data from different clients may follow very different distributions. \\emph{System heterogeneity} refers to client devices having different system capabilities. A considerable number of federated optimization methods address this challenge. In the literature, empirical evaluations usually start federated training from random initialization. However, in many practical applications of federated learning, the server has access to proxy data for the training task that can be used to pre-train a model before starting federated training. Using four standard federated learning benchmark datasets, we empirically study the impact of starting from a pre-trained model in federated learning. Unsurprisingly, starting from a pre-trained model reduces the training time required to reach a target error rate and enables the training of more accurate models (up to 40\\%) than is possible when starting from random initialization. Surprisingly, we also find that starting federated learning from a pre-trained initialization reduces the effect of both data and system heterogeneity. We recommend future work proposing and evaluating federated optimization methods to evaluate the performance when starting from random and pre-trained initializations. This study raises several questions for further work on understanding the role of heterogeneity in federated optimization. \\footnote{Our code is available at: \\url{https://github.com/facebookresearch/where_to_begin}}","url_abs":"https://arxiv.org/abs/2206.15387v3","url_pdf":"https://arxiv.org/pdf/2206.15387v3.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":"where-to-begin-exploring-the-impact-of-pre","repo_url":"https://github.com/facebookresearch/where_to_begin","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"where-to-begin-exploring-the-impact-of-pre","repo_url":"https://github.com/gwenlegate/guidinglastlayerflpretrain","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"federated-learning","task_name":"Federated Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2206.15387","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.15387"}},"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/gwenlegate/guidinglastlayerflpretrain","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/where_to_begin","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran_draft_wrong":2},"by_repo_kind":{"listed":{"samples":2,"ran":2,"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":"19e71cf310816424","entry":"collate_fn","repo":"gwenlegate/guidinglastlayerflpretrain","repo_kind":"listed","path":"src/utils.py","file_url":"https://github.com/gwenlegate/guidinglastlayerflpretrain/blob/HEAD/src/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"19e71cf310816424"}},{"code_sha256_prefix":"781bc729bbe7f17e","entry":"get_data_subset","repo":"gwenlegate/guidinglastlayerflpretrain","repo_kind":"listed","path":"src/utils.py","file_url":"https://github.com/gwenlegate/guidinglastlayerflpretrain/blob/HEAD/src/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"781bc729bbe7f17e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}