Reasonable Effectiveness of Random Weighting: A Litmus Test for Multi-Task Learning
Abstract: Multi-Task Learning (MTL) has achieved success in various fields. However, training with equal weights for all tasks may cause unsatisfactory performance for part of tasks. To address this problem, there are many works to carefully design dynamical loss/gradient weighting strategies but the basic random experiments are ignored to examine their effectiveness. In this paper, we propose the Random Weighting (RW) methods, including Random Loss Weighting (RLW) and Random Gradient Weighting (RGW), where an MTL model is trained with random loss/gradient weights sampled from a distribution. To show the effectiveness and necessity of RW methods, theoretically, we analyze the convergence of RW and reveal that RW has a higher probability to escape local minima, resulting in better generalization ability. Empirically, we extensively evaluate the proposed RW methods to compare with twelve state-of-the-art methods on five image datasets and two multilingual problems from the XTREME benchmark to show that RW methods can achieve comparable performance with state-of-the-art baselines. Therefore, we think the RW methods are important baselines for MTL and should attract more attention.
License: Creative Commons Attribution 4.0 International (CC BY 4.0)
Submission Length: Long submission (more than 12 pages of main content)
Assigned Action Editor: ~Hsuan-Tien_Lin1
Submission Number: 308