Multi-Task Learning as Multi-Objective Optimization

Code

• github.com/IntelVCL/MultiObjectiveOptimization
  Officialpytorch★ 0
• github.com/isl-org/multiobjectiveoptimization
  pytorch★ 1,069
• github.com/ebagdasa/backdoors101
  pytorch★ 378
• github.com/torchjd/torchjd
  pytorch★ 307
• github.com/VICO-UoE/KD4MTL
  pytorch★ 78
• github.com/salomonhotegni/mdmtn
  pytorch★ 16
• github.com/hav4ik/Hydra
  pytorch★ 0

Abstract

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. A common compromise is to optimize a proxy objective that minimizes a weighted linear combination of per-task losses. However, this workaround is only valid when the tasks do not compete, which is rarely the case. In this paper, we explicitly cast multi-task learning as multi-objective optimization, with the overall objective of finding a Pareto optimal solution. To this end, we use algorithms developed in the gradient-based multi-objective optimization literature. These algorithms are not directly applicable to large-scale learning problems since they scale poorly with the dimensionality of the gradients and the number of tasks. We therefore propose an upper bound for the multi-objective loss and show that it can be optimized efficiently. We further prove that optimizing this upper bound yields a Pareto optimal solution under realistic assumptions. We apply our method to a variety of multi-task deep learning problems including digit classification, scene understanding (joint semantic segmentation, instance segmentation, and depth estimation), and multi-label classification. Our method produces higher-performing models than recent multi-task learning formulations or per-task training.

Tasks

Benchmark Results

Reproductions