{"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/a-scale-invariant-task-balancing-approach-for","title":"Dual-Balancing for Multi-Task Learning","arxiv_id":"2308.12029","date":"2023-08-23","proceeding":null,"authors":["Baijiong Lin","Weisen Jiang","Feiyang Ye","Yu Zhang","Pengguang Chen","Ying-Cong Chen","Shu Liu","James T. Kwok"],"abstract":"Multi-task learning (MTL), a learning paradigm to learn multiple related tasks simultaneously, has achieved great success in various fields. However, task balancing problem remains a significant challenge in MTL, with the disparity in loss/gradient scales often leading to performance compromises. In this paper, we propose a Dual-Balancing Multi-Task Learning (DB-MTL) method to alleviate the task balancing problem from both loss and gradient perspectives. Specifically, DB-MTL ensures loss-scale balancing by performing a logarithm transformation on each task loss, and guarantees gradient-magnitude balancing via normalizing all task gradients to the same magnitude as the maximum gradient norm. Extensive experiments conducted on several benchmark datasets consistently demonstrate the state-of-the-art performance of DB-MTL.","url_abs":"https://arxiv.org/abs/2308.12029v2","url_pdf":"https://arxiv.org/pdf/2308.12029v2.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":"a-scale-invariant-task-balancing-approach-for","repo_url":"https://github.com/median-research-group/libmtl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2308.12029","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}