Sample-Level Weighting for Multi-Task Learning with Auxiliary Tasks

2023/06/07 by Emilie Grégoire, Grégoire, Emilie, Hafeez Chaudhary +3 · 2 citations
Computer Science · #Advanced Neural Network Applications #Artificial Intelligence (cs.AI) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #I.2.6 #Machine Learning (cs.LG) #Neural Networks and Applications

paper · pdf · doi:10.48550/arxiv.2306.04519

openalex publication_date 2023/06/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/04

Abstract

Multi-task learning (MTL) can improve the generalization performance of neural networks by sharing representations with related tasks. Nonetheless, MTL can also degrade performance through harmful interference between tasks. Recent work has pursued task-specific loss weighting as a solution for this interference. However, existing algorithms treat tasks as atomic, lacking the ability to explicitly separate harmful and helpful signals beyond the task level. To this end, we propose SLGrad, a sample-level weighting algorithm for multi-task learning with auxiliary tasks. Through sample-specific task weights, SLGrad reshapes the task distributions during training to eliminate harmful auxiliary signals and augment useful task signals. Substantial generalization performance gains are observed on (semi-) synthetic datasets and common supervised multi-task problems.

Cited by

• Generating Auxiliary Tasks with Reinforcement Learning
• Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution

Related

• HydaLearn: Highly Dynamic Task Weighting for Multi-task Learning with Auxiliary Tasks
• Beyond Losses Reweighting: Empowering Multi-Task Learning via the Generalization Perspective
• SLAW: Scaled Loss Approximate Weighting for Efficient Multi-Task Learning
• Analytical Uncertainty-Based Loss Weighting in Multi-Task Learning
• Learning Multi-Tasks with Inconsistent Labels by using Auxiliary Big Task