{"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/towards-multi-modal-transformers-in-federated","title":"Towards Multi-modal Transformers in Federated Learning","arxiv_id":"2404.12467","date":"2024-04-18","proceeding":null,"authors":["Guangyu Sun","Matias Mendieta","Aritra Dutta","Xin Li","Chen Chen"],"abstract":"Multi-modal transformers mark significant progress in different domains, but siloed high-quality data hinders their further improvement. To remedy this, federated learning (FL) has emerged as a promising privacy-preserving paradigm for training models without direct access to the raw data held by different clients. Despite its potential, a considerable research direction regarding the unpaired uni-modal clients and the transformer architecture in FL remains unexplored. To fill this gap, this paper explores a transfer multi-modal federated learning (MFL) scenario within the vision-language domain, where clients possess data of various modalities distributed across different datasets. We systematically evaluate the performance of existing methods when a transformer architecture is utilized and introduce a novel framework called Federated modality complementary and collaboration (FedCola) by addressing the in-modality and cross-modality gaps among clients. Through extensive experiments across various FL settings, FedCola demonstrates superior performance over previous approaches, offering new perspectives on future federated training of multi-modal transformers.","url_abs":"https://arxiv.org/abs/2404.12467v2","url_pdf":"https://arxiv.org/pdf/2404.12467v2.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":"towards-multi-modal-transformers-in-federated","repo_url":"https://github.com/imguangyu/fedcola","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"federated-learning","task_name":"Federated Learning"},{"task_slug":"privacy-preserving","task_name":"Privacy Preserving"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.12467","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.12467"}},"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":"deterministic:regex_extraction","url":"https://github.com/imguangyu/FedCola","reach":null}],"summary":{"ran":7,"ran_draft_wrong":2,"unverified":6},"by_repo_kind":{"official":{"samples":15,"ran":9,"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":"8a67e5c4a6bc779d","entry":"Block","repo":"imguangyu/FedCola","repo_kind":"official","path":"src/models/mome.py","file_url":"https://github.com/imguangyu/FedCola/blob/HEAD/src/models/mome.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8a67e5c4a6bc779d"}},{"code_sha256_prefix":"665d7fe1dc9696b6","entry":"ClassificationHead","repo":"imguangyu/FedCola","repo_kind":"official","path":"src/models/mome.py","file_url":"https://github.com/imguangyu/FedCola/blob/HEAD/src/models/mome.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"665d7fe1dc9696b6"}},{"code_sha256_prefix":"c9f1166f9f9c7f9d","entry":"ImageEmbedding","repo":"imguangyu/FedCola","repo_kind":"official","path":"src/models/mome.py","file_url":"https://github.com/imguangyu/FedCola/blob/HEAD/src/models/mome.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c9f1166f9f9c7f9d"}},{"code_sha256_prefix":"701e39ed251d5829","entry":"LayerScale","repo":"imguangyu/FedCola","repo_kind":"official","path":"src/models/mome.py","file_url":"https://github.com/imguangyu/FedCola/blob/HEAD/src/models/mome.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"701e39ed251d5829"}},{"code_sha256_prefix":"687b410988a1e3fc","entry":"PatchEmbed","repo":"imguangyu/FedCola","repo_kind":"official","path":"src/models/mome.py","file_url":"https://github.com/imguangyu/FedCola/blob/HEAD/src/models/mome.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"687b410988a1e3fc"}},{"code_sha256_prefix":"6440bb445fde338e","entry":"RetrievalHead","repo":"imguangyu/FedCola","repo_kind":"official","path":"src/models/mome.py","file_url":"https://github.com/imguangyu/FedCola/blob/HEAD/src/models/mome.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6440bb445fde338e"}},{"code_sha256_prefix":"70aa8bb289c6319c","entry":"TextEmbedding","repo":"imguangyu/FedCola","repo_kind":"official","path":"src/models/mome.py","file_url":"https://github.com/imguangyu/FedCola/blob/HEAD/src/models/mome.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"70aa8bb289c6319c"}},{"code_sha256_prefix":"5d791ce8029c99b4","entry":"_get_attr_by_name","repo":"imguangyu/FedCola","repo_kind":"official","path":"src/models/mome.py","file_url":"https://github.com/imguangyu/FedCola/blob/HEAD/src/models/mome.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5d791ce8029c99b4"}},{"code_sha256_prefix":"2ca8541c8ffff32a","entry":"build_cross_modal_reparam_linear","repo":"imguangyu/FedCola","repo_kind":"official","path":"src/models/mome.py","file_url":"https://github.com/imguangyu/FedCola/blob/HEAD/src/models/mome.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2ca8541c8ffff32a"}},{"code_sha256_prefix":"b92c5b2c0953da52","entry":"Attention","repo":"imguangyu/FedCola","repo_kind":"official","path":"src/models/mome.py","file_url":"https://github.com/imguangyu/FedCola/blob/HEAD/src/models/mome.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b92c5b2c0953da52"}},{"code_sha256_prefix":"ca1882c73ffb469b","entry":"Embedding","repo":"imguangyu/FedCola","repo_kind":"official","path":"src/models/mome.py","file_url":"https://github.com/imguangyu/FedCola/blob/HEAD/src/models/mome.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ca1882c73ffb469b"}},{"code_sha256_prefix":"1936c941a6de761f","entry":"ModalityAgnosticTransformer","repo":"imguangyu/FedCola","repo_kind":"official","path":"src/models/mome.py","file_url":"https://github.com/imguangyu/FedCola/blob/HEAD/src/models/mome.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1936c941a6de761f"}},{"code_sha256_prefix":"14b77c3b415e19da","entry":"_set_attr_by_name","repo":"imguangyu/FedCola","repo_kind":"official","path":"src/models/mome.py","file_url":"https://github.com/imguangyu/FedCola/blob/HEAD/src/models/mome.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"14b77c3b415e19da"}},{"code_sha256_prefix":"f82635ad6ef8b6e9","entry":"change_original_linear_to_reparam","repo":"imguangyu/FedCola","repo_kind":"official","path":"src/models/mome.py","file_url":"https://github.com/imguangyu/FedCola/blob/HEAD/src/models/mome.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f82635ad6ef8b6e9"}},{"code_sha256_prefix":"4e74ee5ef12c8d25","entry":"reparameterize_aux_into_target_model","repo":"imguangyu/FedCola","repo_kind":"official","path":"src/models/mome.py","file_url":"https://github.com/imguangyu/FedCola/blob/HEAD/src/models/mome.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4e74ee5ef12c8d25"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}