Proactive Gradient Conflict Mitigation in Multi-Task Learning:A Sparse Training Perspective
Preprint
- 10 December 2024
- preprint
- Published by Qeios Ltd in Qeios Preprints
Abstract
Advancing towards generalist agents necessitates the concurrent processing of multiple tasks using a unified model, thereby underscoring the growing significance of simultaneous model training on multiple downstream tasks. A common issue in multi-task learning is the occurrence of gradient conflict, which leads to potential competition among different tasks during joint training. This competition often results in improvements in one task at the expense of deterioration in another. Although several optimization methods have been developed to address this issue by manipulating task gradients for better task balancing, they cannot decrease the incidence of gradient conflict. In this paper, we systematically investigate the occurrence of gradient conflict across different methods and propose a strategy to reduce such conflicts through sparse training (ST), wherein only a portion of the model’s parameters are updated during training while keeping the rest unchanged. Our extensive experiments demonstrate that ST effectively mitigates conflicting gradients and leads to superior performance. Furthermore, ST can be easily integrated with gradient manipulation techniques, thus enhancing their effectiveness.Keywords
All Related Versions
This publication has 24 references indexed in Scilit:
- Attentive Single-Tasking of Multiple Tasks2019
- Pattern-Affinitive Propagation Across Depth, Surface Normal and Semantic Segmentation2019
- End-To-End Multi-Task Learning With Attention2019
- Joint Task-Recursive Learning for Semantic Segmentation and Depth Estimation2018
- Multi-task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics2018
- PAD-Net: Multi-tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsing2018
- The Cityscapes Dataset for Semantic Urban Scene Understanding2016
- Cross-Stitch Networks for Multi-task Learning2016
- Deep Learning Face Attributes in the Wild2015
- ImageNet: A large-scale hierarchical image database2009