Multi-Task Learning as Multi-Objective Optimization

NeurIPS 2018 Ozan SenerVladlen Koltun

In multi-task learning, multiple tasks are solved jointly, sharing inductive bias between them. Multi-task learning is inherently a multi-objective problem because different tasks may conflict, necessitating a trade-off... (read more)

PDF Abstract

Evaluation results from the paper


Task Dataset Model Metric name Metric value Global rank Compare
Multi-Task Learning CelebA MGDA-UB Error 8.25 # 1
Multi-Task Learning Cityscapes test MultiObjectiveOptimization mIoU 66.63 # 1