{"type":"ScholarlyArticle","title":"Injecting Imbalance Sensitivity for Multi-Task Learning","authors":[{"name":"Zhipeng Zhou","slug":"zhipeng-zhou","given":"Zhipeng","family":"Zhou","affiliation":""},{"name":"Liu Liu","slug":"liu-liu","given":"Liu","family":"Liu","affiliation":""},{"name":"Peilin Zhao","slug":"peilin-zhao","given":"Peilin","family":"Zhao","affiliation":""},{"name":"Wei Gong","slug":"wei-gong","given":"Wei","family":"Gong","affiliation":""}],"abstract":"Multi-task learning (MTL) has emerged as a promising approach for deploying deep learning models in real-life applications. Recent studies have proposed optimization-based learning paradigms to establish task-shared representations in MTL. However, our paper empirically argues that these studies, specifically gradient-based ones, primarily emphasize the conflict issue while neglecting the potentially more significant impact of imbalance/dominance in MTL. In line with this perspective, we enhance the existing baseline method by injecting imbalance-sensitivity through the imposition of constraints on the projected norms. To demonstrate the effectiveness of our proposed IMbalance-sensitive Gradient (IMGrad) descent method, we evaluate it on multiple mainstream MTL benchmarks, encompassing supervised learning tasks as well as reinforcement learning. The experimental results consistently demonstrate competitive performance.","doi":"10.24963/ijcai.2025/805","url":"https://ijcai.org/proceedings/2025/805","pdf":"https://ijcai.org/proceedings/2025/0805.pdf","markdown":"https://ijcai.org/proceedings/2025/805.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/805","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Machine Learning","track":"Main Track","number":805,"pages":{"first":7236,"last":7244},"keywords":["Machine Learning: ML: Multi-task and transfer learning","Machine Learning: ML: Meta-learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}