{"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/multi-task-learning-as-a-bargaining-game","title":"Multi-Task Learning as a Bargaining Game","arxiv_id":"2202.01017","date":"2022-02-02","proceeding":null,"authors":["Aviv Navon","Aviv Shamsian","Idan Achituve","Haggai Maron","Kenji Kawaguchi","Gal Chechik","Ethan Fetaya"],"abstract":"In Multi-task learning (MTL), a joint model is trained to simultaneously make predictions for several tasks. Joint training reduces computation costs and improves data efficiency; however, since the gradients of these different tasks may conflict, training a joint model for MTL often yields lower performance than its corresponding single-task counterparts. A common method for alleviating this issue is to combine per-task gradients into a joint update direction using a particular heuristic. In this paper, we propose viewing the gradients combination step as a bargaining game, where tasks negotiate to reach an agreement on a joint direction of parameter update. Under certain assumptions, the bargaining problem has a unique solution, known as the Nash Bargaining Solution, which we propose to use as a principled approach to multi-task learning. We describe a new MTL optimization procedure, Nash-MTL, and derive theoretical guarantees for its convergence. Empirically, we show that Nash-MTL achieves state-of-the-art results on multiple MTL benchmarks in various domains.","url_abs":"https://arxiv.org/abs/2202.01017v2","url_pdf":"https://arxiv.org/pdf/2202.01017v2.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":"multi-task-learning-as-a-bargaining-game","repo_url":"https://github.com/avivnavon/nash-mtl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multi-task-learning-as-a-bargaining-game","repo_url":"https://github.com/autumn9999/go4align","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multi-task-learning-as-a-bargaining-game","repo_url":"https://github.com/cranial-xix/famo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multi-task-learning-as-a-bargaining-game","repo_url":"https://github.com/torchjd/torchjd","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/multi-task-learning-on-cityscapes","task":"Multi-Task Learning","dataset":"Cityscapes test","model":"Nash-MTL","rank_in_archive_order":2,"of":3,"metrics":{"mIoU":"75.41"},"uses_additional_data":false},{"leaderboard":"/sota/multi-task-learning-on-nyuv2","task":"Multi-Task Learning","dataset":"NYUv2","model":"Nash-MTL","rank_in_archive_order":2,"of":2,"metrics":{"Mean IoU":"40.13"},"uses_additional_data":false},{"leaderboard":"/sota/multi-task-learning-on-qm9","task":"Multi-Task Learning","dataset":"QM9","model":"Nash-MTL","rank_in_archive_order":2,"of":5,"metrics":{"∆m%":"62.0"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2202.01017","atlas_url":"https://app.syntology.ai/?focus=2202.01017","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.01017"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/AvivNavon/nash-mtl","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cranial-xix/famo","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/avivnavon/nash-mtl","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/autumn9999/go4align","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/torchjd/torchjd","reach":null}],"summary":{"ran":1,"unverified":2},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1},"listed":{"samples":2,"ran":1,"repositories":2}},"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":2,"samples":[{"code_sha256_prefix":"6ec7450b6d8b25a1","entry":"NashMTL","repo":"cranial-xix/famo","repo_kind":"listed","path":"methods/weight_methods.py","file_url":"https://github.com/cranial-xix/famo/blob/HEAD/methods/weight_methods.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":"6ec7450b6d8b25a1"}},{"code_sha256_prefix":"2243fe3125059d36","entry":"NashMTL","repo":"autumn9999/go4align","repo_kind":"listed","path":"methods/weight_methods.py","file_url":"https://github.com/autumn9999/go4align/blob/HEAD/methods/weight_methods.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2243fe3125059d36"}},{"code_sha256_prefix":"def129ab34b9f0f8","entry":"gradient_normalizers","repo":"AvivNavon/nash-mtl","repo_kind":"official","path":"methods/min_norm_solvers.py","file_url":"https://github.com/AvivNavon/nash-mtl/blob/HEAD/methods/min_norm_solvers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"def129ab34b9f0f8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}