Pareto Manifold Learning: Tackling multiple tasks via ensembles of single-task models
This addresses the need for flexible trade-off balancing in multi-task learning for practitioners, though it is incremental as it builds on existing Pareto Front parameterization methods.
The paper tackles the problem of multi-task learning where tasks compete, proposing Pareto Manifold Learning to learn a continuous Pareto Front via ensembling in weight space, and it outperforms state-of-the-art single-point algorithms and learns better Pareto parameterizations than multi-point baselines.
In Multi-Task Learning (MTL), tasks may compete and limit the performance achieved on each other, rather than guiding the optimization to a solution, superior to all its single-task trained counterparts. Since there is often not a unique solution optimal for all tasks, practitioners have to balance tradeoffs between tasks' performance, and resort to optimality in the Pareto sense. Most MTL methodologies either completely neglect this aspect, and instead of aiming at learning a Pareto Front, produce one solution predefined by their optimization schemes, or produce diverse but discrete solutions. Recent approaches parameterize the Pareto Front via neural networks, leading to complex mappings from tradeoff to objective space. In this paper, we conjecture that the Pareto Front admits a linear parameterization in parameter space, which leads us to propose \textit{Pareto Manifold Learning}, an ensembling method in weight space. Our approach produces a continuous Pareto Front in a single training run, that allows to modulate the performance on each task during inference. Experiments on multi-task learning benchmarks, ranging from image classification to tabular datasets and scene understanding, show that \textit{Pareto Manifold Learning} outperforms state-of-the-art single-point algorithms, while learning a better Pareto parameterization than multi-point baselines.