# Multitask Learning with Single Gradient Step Update for Task Balancing

arXiv: https://arxiv.org/abs/2005.09910 · HTML: https://mlsanity.com/paper/2005.09910/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 May 2020.

## Built on by (most cited first, 9 of 9)

- [Heterogeneous Multi-task Learning with Expert Diversity](https://mlsanity.com/paper/2106.10595/) (2021)
- [Multi-Objective Learning to Predict Pareto Fronts Using Hypervolume Maximization](https://mlsanity.com/paper/2102.04523/) (2021)
- [A Transformer-Based Deep Learning Approach for Fairly Predicting Post-Liver Transplant Risk Factors](https://mlsanity.com/paper/2304.02780/) (2023)
- [Learning Twofold Heterogeneous Multi-Task by Sharing Similar Convolution Kernel Pairs](https://mlsanity.com/paper/2101.12431/) (2021)
- [Learning Multi-Tasks with Inconsistent Labels by using Auxiliary Big Task](https://mlsanity.com/paper/2201.02305/) (2022)
- [UV-M3TL: A Unified and Versatile Multimodal Multi-Task Learning Framework for Assistive Driving Perception](https://mlsanity.com/paper/2602.01594/) (2026)
- [Learning Representation for Multitask learning through Self Supervised Auxiliary learning](https://mlsanity.com/paper/2409.16651/) (2024)
- [Advances in Electron Microscopy with Deep Learning](https://mlsanity.com/paper/2101.01178/) (2021)
- [Motivation is Something You Need](https://mlsanity.com/paper/2602.21064/) (2026)

## Abstract (arXiv)

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.