{"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/l-dawa-layer-wise-divergence-aware-weight","title":"L-DAWA: Layer-wise Divergence Aware Weight Aggregation in Federated Self-Supervised Visual Representation Learning","arxiv_id":"2307.07393","date":"2023-07-14","proceeding":"ICCV 2023 1","authors":["Yasar Abbas Ur Rehman","Yan Gao","Pedro Porto Buarque de Gusmão","Mina Alibeigi","Jiajun Shen","Nicholas D. Lane"],"abstract":"The ubiquity of camera-enabled devices has led to large amounts of unlabeled image data being produced at the edge. The integration of self-supervised learning (SSL) and federated learning (FL) into one coherent system can potentially offer data privacy guarantees while also advancing the quality and robustness of the learned visual representations without needing to move data around. However, client bias and divergence during FL aggregation caused by data heterogeneity limits the performance of learned visual representations on downstream tasks. In this paper, we propose a new aggregation strategy termed Layer-wise Divergence Aware Weight Aggregation (L-DAWA) to mitigate the influence of client bias and divergence during FL aggregation. The proposed method aggregates weights at the layer-level according to the measure of angular divergence between the clients' model and the global model. Extensive experiments with cross-silo and cross-device settings on CIFAR-10/100 and Tiny ImageNet datasets demonstrate that our methods are effective and obtain new SOTA performance on both contrastive and non-contrastive SSL approaches.","url_abs":"https://arxiv.org/abs/2307.07393v1","url_pdf":"https://arxiv.org/pdf/2307.07393v1.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":"l-dawa-layer-wise-divergence-aware-weight","repo_url":"https://github.com/yasar-rehman/L-DAWA","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"federated-learning","task_name":"Federated Learning"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"}],"methods":[{"method_slug":"aware","method_name":"AWARE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2307.07393","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.07393"}},"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/yasar-rehman/L-DAWA","reach":{"status":"ok"}}],"summary":{"ran":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"76c22d310ccf456e","entry":"load_json","repo":"yasar-rehman/L-DAWA","repo_kind":"official","path":"Data_distribution_generation/CIFAR10_json_splitter_direchlet.py","file_url":"https://github.com/yasar-rehman/L-DAWA/blob/HEAD/Data_distribution_generation/CIFAR10_json_splitter_direchlet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"76c22d310ccf456e"}},{"code_sha256_prefix":"02ac62de32500ed7","entry":"load_transforms_FED","repo":"yasar-rehman/L-DAWA","repo_kind":"official","path":"inventory/src/datasets/datasets.py","file_url":"https://github.com/yasar-rehman/L-DAWA/blob/HEAD/inventory/src/datasets/datasets.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"02ac62de32500ed7"}},{"code_sha256_prefix":"ac0d97676f99e68a","entry":"zscore_image","repo":"yasar-rehman/L-DAWA","repo_kind":"official","path":"inventory/src/datasets/datasets.py","file_url":"https://github.com/yasar-rehman/L-DAWA/blob/HEAD/inventory/src/datasets/datasets.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ac0d97676f99e68a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}