Reasonable Effectiveness of Random Weighting: A Litmus Test for Multi-Task Learning

TL;DR

This paper introduces Random Weighting methods for multi-task learning, demonstrating their theoretical advantages in escaping local minima and empirically showing they perform comparably to state-of-the-art methods across various datasets.

Contribution

The paper proposes simple yet effective Random Weighting methods for MTL, providing theoretical analysis and extensive empirical validation as strong baselines.

Findings

RW methods can escape local minima more effectively.

RW methods achieve comparable performance to state-of-the-art.

RW methods are important baselines for future MTL research.

Abstract

Multi-Task Learning (MTL) has achieved success in various fields. However, how to balance different tasks to achieve good performance is a key problem. To achieve the task balancing, 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 RW methods can achieve comparable performance with state-of-the-art baselines. Therefore, we think that the RW methods are important baselines for MTL and should attract more attentions.