{"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/fedmax-mitigating-activation-divergence-for","title":"FedMAX: Mitigating Activation Divergence for Accurate and Communication-Efficient Federated Learning","arxiv_id":"2004.03657","date":"2020-04-07","proceeding":null,"authors":["Wei Chen","Kartikeya Bhardwaj","Radu Marculescu"],"abstract":"In this paper, we identify a new phenomenon called activation-divergence which occurs in Federated Learning (FL) due to data heterogeneity (i.e., data being non-IID) across multiple users. Specifically, we argue that the activation vectors in FL can diverge, even if subsets of users share a few common classes with data residing on different devices. To address the activation-divergence issue, we introduce a prior based on the principle of maximum entropy; this prior assumes minimal information about the per-device activation vectors and aims at making the activation vectors of same classes as similar as possible across multiple devices. Our results show that, for both IID and non-IID settings, our proposed approach results in better accuracy (due to the significantly more similar activation vectors across multiple devices), and is more communication-efficient than state-of-the-art approaches in FL. Finally, we illustrate the effectiveness of our approach on a few common benchmarks and two large medical datasets.","url_abs":"https://arxiv.org/abs/2004.03657v2","url_pdf":"https://arxiv.org/pdf/2004.03657v2.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":"fedmax-mitigating-activation-divergence-for","repo_url":"https://github.com/weichennone/FedMAX","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"federated-learning","task_name":"Federated Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2004.03657","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.03657"}},"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/weichennone/FedMAX","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"ran_draft_wrong":1,"unverified":12},"by_repo_kind":{"listed":{"samples":14,"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":"616b5e82dd2a38f9","entry":"count_params","repo":"weichennone/FedMAX","repo_kind":"listed","path":"medical_data/lib/utils.py","file_url":"https://github.com/weichennone/FedMAX/blob/HEAD/medical_data/lib/utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"616b5e82dd2a38f9"}},{"code_sha256_prefix":"f9964d719c5cb8f4","entry":"FedAvg","repo":"weichennone/FedMAX","repo_kind":"listed","path":"digit_object_recognition/models/Fed.py","file_url":"https://github.com/weichennone/FedMAX/blob/HEAD/digit_object_recognition/models/Fed.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f9964d719c5cb8f4"}},{"code_sha256_prefix":"913d82af53065418","entry":"accuracy","repo":"weichennone/FedMAX","repo_kind":"listed","path":"medical_data/lib/utils.py","file_url":"https://github.com/weichennone/FedMAX/blob/HEAD/medical_data/lib/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"913d82af53065418"}},{"code_sha256_prefix":"6b0f40ddd37b7b2c","entry":"cifar_iid","repo":"weichennone/FedMAX","repo_kind":"listed","path":"digit_object_recognition/utils/sampling.py","file_url":"https://github.com/weichennone/FedMAX/blob/HEAD/digit_object_recognition/utils/sampling.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":"6b0f40ddd37b7b2c"}},{"code_sha256_prefix":"a2be42588b41c16d","entry":"cifar_noniid_2","repo":"weichennone/FedMAX","repo_kind":"listed","path":"digit_object_recognition/utils/sampling.py","file_url":"https://github.com/weichennone/FedMAX/blob/HEAD/digit_object_recognition/utils/sampling.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":"a2be42588b41c16d"}},{"code_sha256_prefix":"28952daced30ce4d","entry":"confusion_mat","repo":"weichennone/FedMAX","repo_kind":"listed","path":"medical_data/lib/metrics.py","file_url":"https://github.com/weichennone/FedMAX/blob/HEAD/medical_data/lib/metrics.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":"28952daced30ce4d"}},{"code_sha256_prefix":"5c35afeaa0ba402f","entry":"f1_micro","repo":"weichennone/FedMAX","repo_kind":"listed","path":"medical_data/lib/metrics.py","file_url":"https://github.com/weichennone/FedMAX/blob/HEAD/medical_data/lib/metrics.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":"5c35afeaa0ba402f"}},{"code_sha256_prefix":"55fcb483356a9173","entry":"fedavg","repo":"weichennone/FedMAX","repo_kind":"listed","path":"medical_data/fed.py","file_url":"https://github.com/weichennone/FedMAX/blob/HEAD/medical_data/fed.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":"55fcb483356a9173"}},{"code_sha256_prefix":"f08f5ccff4b9f848","entry":"femnist_star","repo":"weichennone/FedMAX","repo_kind":"listed","path":"digit_object_recognition/utils/sampling.py","file_url":"https://github.com/weichennone/FedMAX/blob/HEAD/digit_object_recognition/utils/sampling.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":"f08f5ccff4b9f848"}},{"code_sha256_prefix":"f7cae9b5a404a4a3","entry":"normalize","repo":"weichennone/FedMAX","repo_kind":"listed","path":"medical_data/lib/preprocess.py","file_url":"https://github.com/weichennone/FedMAX/blob/HEAD/medical_data/lib/preprocess.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":"f7cae9b5a404a4a3"}},{"code_sha256_prefix":"32a4630f4052c270","entry":"quadratic_weighted_kappa","repo":"weichennone/FedMAX","repo_kind":"listed","path":"medical_data/lib/metrics.py","file_url":"https://github.com/weichennone/FedMAX/blob/HEAD/medical_data/lib/metrics.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":"32a4630f4052c270"}},{"code_sha256_prefix":"6e2803e2d089d093","entry":"remove_boundaries","repo":"weichennone/FedMAX","repo_kind":"listed","path":"medical_data/lib/preprocess.py","file_url":"https://github.com/weichennone/FedMAX/blob/HEAD/medical_data/lib/preprocess.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":"6e2803e2d089d093"}},{"code_sha256_prefix":"0079a1a6108a54b6","entry":"scale_radius","repo":"weichennone/FedMAX","repo_kind":"listed","path":"medical_data/lib/preprocess.py","file_url":"https://github.com/weichennone/FedMAX/blob/HEAD/medical_data/lib/preprocess.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":"0079a1a6108a54b6"}},{"code_sha256_prefix":"2e468cbd0d4a4241","entry":"str2bool","repo":"weichennone/FedMAX","repo_kind":"listed","path":"medical_data/lib/utils.py","file_url":"https://github.com/weichennone/FedMAX/blob/HEAD/medical_data/lib/utils.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":"2e468cbd0d4a4241"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}