为多任务学习注入不平衡敏感性

Mar, 2025

Injecting Imbalance Sensitivity for Multi-Task Learning

Zhipeng Zhou, Liu Liu, Peilin Zhao, Wei Gong

TL;DR本研究解决了多任务学习中存在的任务不平衡问题，并提出通过施加约束的方式增强现有基线方法的有效性。关键的创新在于引入了不平衡敏感的梯度下降(IMGrad)方法，实验结果显示，在多个主流的多任务学习基准上表现优异，具有重要的实际应用价值。

Abstract

Multi-task Learning (MTL) has emerged as a promising approach for deploying Deep Learning models in real-life applications. Recent studies have proposed optimization-based learning paradigms to establish task-sha