#5810. Multitask learning with single gradient step update for task balancing

June 2026publication date
Proposal available till 15-05-2025
4 total number of authors per manuscript0 $

The title of the journal is available only for the authors who have already paid for
Journal’s subject area:
Cognitive Neuroscience;
Computer Science Applications;
Artificial Intelligence;
Places in the authors’ list:
place 1place 2place 3place 4
FreeFreeFreeFree
2350 $1200 $1050 $900 $
Contract №5810.1 Contract №5810.2 Contract №5810.3 Contract №5810.4
1 place - free (for sale)
2 place - free (for sale)
3 place - free (for sale)
4 place - free (for sale)

Abstract:
Multitask learning is a methodology to boost generalization performance and also reduce computational intensity and memory usage. However, learning multiple tasks simultaneously can be more difficult than learning a single task because it can cause imbalance among tasks. To address the imbalance problem, we propose an algorithm to balance between tasks at the gradient level by applying gradient-based meta-learning to multitask learning. The proposed method trains shared layers and task-specific layers separately so that the two layers with different roles in a multitask network can be fitted to their own purposes. In particular, the shared layer that contains informative knowledge shared among tasks is trained by employing single gradient step update and inner/outer loop training to mitigate the imbalance problem at the gradient level. We apply the proposed method to various multitask computer vision problems and achieve state-of-the-art performance.
Keywords:
Convolution neural network; Deep learning; Gradient-based meta learning; Multitask learning

Contacts :
0