{"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/fedconv-enhancing-convolutional-neural","title":"FedConv: Enhancing Convolutional Neural Networks for Handling Data Heterogeneity in Federated Learning","arxiv_id":"2310.04412","date":"2023-10-06","proceeding":null,"authors":["Peiran Xu","Zeyu Wang","Jieru Mei","Liangqiong Qu","Alan Yuille","Cihang Xie","Yuyin Zhou"],"abstract":"Federated learning (FL) is an emerging paradigm in machine learning, where a shared model is collaboratively learned using data from multiple devices to mitigate the risk of data leakage. While recent studies posit that Vision Transformer (ViT) outperforms Convolutional Neural Networks (CNNs) in addressing data heterogeneity in FL, the specific architectural components that underpin this advantage have yet to be elucidated. In this paper, we systematically investigate the impact of different architectural elements, such as activation functions and normalization layers, on the performance within heterogeneous FL. Through rigorous empirical analyses, we are able to offer the first-of-its-kind general guidance on micro-architecture design principles for heterogeneous FL. Intriguingly, our findings indicate that with strategic architectural modifications, pure CNNs can achieve a level of robustness that either matches or even exceeds that of ViTs when handling heterogeneous data clients in FL. Additionally, our approach is compatible with existing FL techniques and delivers state-of-the-art solutions across a broad spectrum of FL benchmarks. The code is publicly available at https://github.com/UCSC-VLAA/FedConv","url_abs":"https://arxiv.org/abs/2310.04412v1","url_pdf":"https://arxiv.org/pdf/2310.04412v1.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":"fedconv-enhancing-convolutional-neural","repo_url":"https://github.com/ucsc-vlaa/fedconv","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"federated-learning","task_name":"Federated Learning"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.04412","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.04412"}},"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/ucsc-vlaa/fedconv","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":4,"ran_draft_wrong":2,"ran":5,"ran_honours":1,"unverified":6},"by_repo_kind":{"official":{"samples":18,"ran":12,"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":"7d8eaf5537f699e4","entry":"np2th","repo":"ucsc-vlaa/fedconv","repo_kind":"official","path":"models/modeling.py","file_url":"https://github.com/ucsc-vlaa/fedconv/blob/HEAD/models/modeling.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7d8eaf5537f699e4"}},{"code_sha256_prefix":"0f786c407fb1ee4c","entry":"swish","repo":"ucsc-vlaa/fedconv","repo_kind":"official","path":"models/modeling.py","file_url":"https://github.com/ucsc-vlaa/fedconv/blob/HEAD/models/modeling.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0f786c407fb1ee4c"}},{"code_sha256_prefix":"144d10b49baeb8a6","entry":"window_partition","repo":"ucsc-vlaa/fedconv","repo_kind":"official","path":"models/swin_mlp.py","file_url":"https://github.com/ucsc-vlaa/fedconv/blob/HEAD/models/swin_mlp.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"144d10b49baeb8a6"}},{"code_sha256_prefix":"6ada0865c90c900f","entry":"downsample_avg","repo":"ucsc-vlaa/fedconv","repo_kind":"official","path":"models/fedconv.py","file_url":"https://github.com/ucsc-vlaa/fedconv/blob/HEAD/models/fedconv.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":"6ada0865c90c900f"}},{"code_sha256_prefix":"88a1713383891daf","entry":"downsample_avg","repo":"ucsc-vlaa/fedconv","repo_kind":"official","path":"models/resnet.py","file_url":"https://github.com/ucsc-vlaa/fedconv/blob/HEAD/models/resnet.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":"88a1713383891daf"}},{"code_sha256_prefix":"b40029fec7094af6","entry":"downsample_conv","repo":"ucsc-vlaa/fedconv","repo_kind":"official","path":"models/fedconv.py","file_url":"https://github.com/ucsc-vlaa/fedconv/blob/HEAD/models/fedconv.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":"b40029fec7094af6"}},{"code_sha256_prefix":"eea0376ea397a1c7","entry":"downsample_conv","repo":"ucsc-vlaa/fedconv","repo_kind":"official","path":"models/resnet.py","file_url":"https://github.com/ucsc-vlaa/fedconv/blob/HEAD/models/resnet.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":"eea0376ea397a1c7"}},{"code_sha256_prefix":"9b02c1068795fd5b","entry":"get_padding","repo":"ucsc-vlaa/fedconv","repo_kind":"official","path":"models/fedconv.py","file_url":"https://github.com/ucsc-vlaa/fedconv/blob/HEAD/models/fedconv.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9b02c1068795fd5b"}},{"code_sha256_prefix":"926911eaf7b09162","entry":"register_notrace_function","repo":"ucsc-vlaa/fedconv","repo_kind":"official","path":"models/fx_features.py","file_url":"https://github.com/ucsc-vlaa/fedconv/blob/HEAD/models/fx_features.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":"926911eaf7b09162"}},{"code_sha256_prefix":"191b2735955d18f4","entry":"resize_pos_embed","repo":"ucsc-vlaa/fedconv","repo_kind":"official","path":"models/vision_transformers.py","file_url":"https://github.com/ucsc-vlaa/fedconv/blob/HEAD/models/vision_transformers.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"191b2735955d18f4"}},{"code_sha256_prefix":"80c66c535be6f491","entry":"window_partition","repo":"ucsc-vlaa/fedconv","repo_kind":"official","path":"models/swin_transformer.py","file_url":"https://github.com/ucsc-vlaa/fedconv/blob/HEAD/models/swin_transformer.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"80c66c535be6f491"}},{"code_sha256_prefix":"61bf152e6a42a184","entry":"window_reverse","repo":"ucsc-vlaa/fedconv","repo_kind":"official","path":"models/swin_mlp.py","file_url":"https://github.com/ucsc-vlaa/fedconv/blob/HEAD/models/swin_mlp.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"61bf152e6a42a184"}},{"code_sha256_prefix":"15181f7956a00a9b","entry":"build_model","repo":"ucsc-vlaa/fedconv","repo_kind":"official","path":"models/build.py","file_url":"https://github.com/ucsc-vlaa/fedconv/blob/HEAD/models/build.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":"15181f7956a00a9b"}},{"code_sha256_prefix":"74147d576b3e7b3b","entry":"build_model","repo":"ucsc-vlaa/fedconv","repo_kind":"official","path":"models/build_orig.py","file_url":"https://github.com/ucsc-vlaa/fedconv/blob/HEAD/models/build_orig.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":"74147d576b3e7b3b"}},{"code_sha256_prefix":"6d8a1f8a0697180f","entry":"checkpoint_filter_fn","repo":"ucsc-vlaa/fedconv","repo_kind":"official","path":"models/vision_transformers.py","file_url":"https://github.com/ucsc-vlaa/fedconv/blob/HEAD/models/vision_transformers.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":"6d8a1f8a0697180f"}},{"code_sha256_prefix":"cd2a47ded9dd84cf","entry":"is_model","repo":"ucsc-vlaa/fedconv","repo_kind":"official","path":"models/registry.py","file_url":"https://github.com/ucsc-vlaa/fedconv/blob/HEAD/models/registry.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":"cd2a47ded9dd84cf"}},{"code_sha256_prefix":"d14a6ca5ff9d530e","entry":"list_models","repo":"ucsc-vlaa/fedconv","repo_kind":"official","path":"models/registry.py","file_url":"https://github.com/ucsc-vlaa/fedconv/blob/HEAD/models/registry.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":"d14a6ca5ff9d530e"}},{"code_sha256_prefix":"e13039fb1c347452","entry":"register_model","repo":"ucsc-vlaa/fedconv","repo_kind":"official","path":"models/registry.py","file_url":"https://github.com/ucsc-vlaa/fedconv/blob/HEAD/models/registry.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":"e13039fb1c347452"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}