Proceedings

Injecting Imbalance Sensitivity for Multi-Task Learning

Zhipeng Zhou, Liu Liu, Peilin Zhao, Wei Gong

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 7236-7244.

https://doi.org/10.24963/ijcai.2025/805

Keywords

  • Machine Learning: ML: Multi-task and transfer learning
  • Machine Learning: ML: Meta-learning

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.

Zhipeng Zhou, Liu Liu, Peilin Zhao, and Wei Gong. 2025. Injecting Imbalance Sensitivity for Multi-Task Learning. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 7236–7244. https://doi.org/10.24963/ijcai.2025/805
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards