AdaTask: A Task-Aware Adaptive Learning Rate Approach to Multi-Task Learning
Open Access
- 26 June 2023
- journal article
- research article
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 37 (9) , 10745-10753
Abstract
Multi-task learning (MTL) models have demonstrated impressive results in computer vision, natural language processing, and recommender systems. Even though many approaches have been proposed, how well these approaches balance different tasks on each parameter still remains unclear. In this paper, we propose to measure the task dominance degree of a parameter by the total updates of each task on this parameter. Specifically, we compute the total updates by the exponentially decaying Average of the squared Updates (AU) on a parameter from the corresponding task. Based on this novel metric, we observe that many parameters in existing MTL methods, especially those in the higher shared layers, are still dominated by one or several tasks. The dominance of AU is mainly due to the dominance of accumulative gradients from one or several tasks. Motivated by this, we propose a Task-wise Adaptive learning rate approach, AdaTask in short, to separate the accumulative gradients and hence the learning rate of each task for each parameter in adaptive learning rate approaches (e.g., AdaGrad, RMSProp, and Adam). Comprehensive experiments on computer vision and recommender system MTL datasets demonstrate that AdaTask significantly improves the performance of dominated tasks, resulting SOTA average task-wise performance. Analysis on both synthetic and real-world datasets shows AdaTask balance parameters in every shared layer well.Keywords
All Related Versions
This publication has 18 references indexed in Scilit:
- Personalized Approximate Pareto-Efficient Recommendation2021
- Progressive Layered Extraction (PLE): A Novel Multi-Task Learning (MTL) Model for Personalized Recommendations2020
- Multiple Relational Attention Network for Multi-task Learning2019
- Predicting Different Types of Conversions with Multi-Task Learning in Online Advertising2019
- A Sufficient Condition for Convergences of Adam and RMSProp2019
- Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts2018
- Multi-task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics2018
- Taskonomy: Disentangling Task Transfer Learning2018
- Cross-Stitch Networks for Multi-task Learning2016
- On the momentum term in gradient descent learning algorithmsNeural Networks, 1999