{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/towards-impartial-multi-task-learning","title":"Towards Impartial Multi-task Learning","arxiv_id":null,"date":"2021-01-01","proceeding":"ICLR 2021 1","authors":["Liyang Liu","Yi Li","Zhanghui Kuang","Jing-Hao Xue","Yimin Chen","Wenming Yang","Qingmin Liao","Wayne Zhang"],"abstract":"Multi-task learning (MTL) has been widely used in representation learning. However, naively training all tasks simultaneously may lead to the partial training issue, where specific tasks are trained more adequately than others. In this paper, we propose to learn multiple tasks impartially. Specifically, for the task-shared parameters, we optimize the scaling factors via a closed-form solution, such that the aggregated gradient (sum of raw gradients weighted by the scaling factors) has equal projections onto individual tasks. For the task-specific parameters, we dynamically weigh the task losses so that all of them are kept at a comparable scale. Further, we find the above gradient balance and loss balance are complementary and thus propose a hybrid balance method to further improve the performance. Our impartial multi-task learning (IMTL) can be end-to-end trained without any heuristic hyper-parameter tuning, and is general to be applied on all kinds of losses without any distribution assumption. Moreover, our IMTL can converge to similar results even when the task losses are designed to have different scales, and thus it is scale-invariant. We extensively evaluate our IMTL on the standard MTL benchmarks including Cityscapes, NYUv2 and CelebA. It achieves the new state-of-the-art and outperforms its competitors remarkably.","url_abs":"https://openreview.net/forum?id=IMPnRXEWpvr","url_pdf":"https://openreview.net/pdf?id=IMPnRXEWpvr","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-impartial-multi-task-learning","repo_url":"https://github.com/JohnLaMaster/Impartial_Multi-Task_Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"towards-impartial-multi-task-learning","repo_url":"https://github.com/avivnavon/nash-mtl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"towards-impartial-multi-task-learning","repo_url":"https://github.com/torchjd/torchjd","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"no_arxiv_id","checked_against":null,"by_repo":[{"repo":"JohnLaMaster/Impartial_Multi-Task_Learning","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"avivnavon/nash-mtl","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":2,"harvested_for":["2001.06782","2202.01017"],"harvested_for_calls":[{"arxiv_id":"2001.06782","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2001.06782"},"call":"get_harvested_code_for_paper(arxiv_id=\"2001.06782\")"},{"arxiv_id":"2202.01017","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2202.01017"},"call":"get_harvested_code_for_paper(arxiv_id=\"2202.01017\")"}]},{"repo":"torchjd/torchjd","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2010.06808"],"harvested_for_calls":[{"arxiv_id":"2010.06808","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2010.06808"},"call":"get_harvested_code_for_paper(arxiv_id=\"2010.06808\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"b7cb3f0f1c5a749edf0909a0eda27c04c6dd1f9beb54b56dae5892ea14636f29","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}