GO4Align: Group Optimization for Multi-Task Alignment

This paper proposes GO4Align, a multi-task optimization approach that tackles task imbalance by explicitly aligning the optimization across tasks. To achieve this, we design an adaptive group risk minimization strategy, comprising two techniques in implementation: (i) dynamical group assignment, which clusters similar tasks based on task interactions; (ii) risk-guided group indicators, which exploit consistent task correlations with risk information from previous iterations. Comprehensive experimental results on diverse benchmarks demonstrate our method's performance superiority with even lower computational costs.

Authors

• Jiayi Shen
• Qi Wang
• Zehao Xiao
• Nanne van Noord University of Amsterdam
• Marcel Worring University of Amsterdam

Keywords

No keywords are indexed for this paper.