Part of Advances in Neural Information Processing Systems 37 (NeurIPS 2024) Main Conference Track
Jiayi Shen, Qi Wang, Zehao Xiao, Nanne van Noord, Marcel Worring
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.