arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2010.06313cs.LGstat.ML
收藏

可控Pareto多任务学习

Controllable Pareto Multi-Task Learning

City University of Hong Kong(香港城市大学)

Xi Lin, Zhiyuan Yang, Qingfu Zhang, Sam Kwong

摘要:

多任务学习(MTL)系统旨在同时解决多个相关任务。在模型容量固定的情况下,任务之间会发生冲突,系统通常不得不在学习所有任务之间进行权衡。对于许多必须在线进行权衡的现实应用程序,必须训练和存储对任务具有不同偏好的多个模型。提出了一种新的可控Pareto多任务学习框架,使系统能够在单一模型下对不同任务进行实时的权衡控制。具体来说,我们制定的MTL作为一个偏好条件的多目标优化问题,从偏好的参数映射到相应的权衡解决方案。建立一个基于超网络的多任务神经网络来学习具有不同权衡偏好的所有任务,其中超网络根据偏好生成模型参数。对于推理,MTL从业者可以根据不同的权衡偏好实时轻松控制模型性能。不同应用的实验表明,该模型是有效的解决各种MTL问题。

英文摘要:

A multi-task learning (MTL) system aims at solving multiple related tasks at the same time. With a fixed model capacity, the tasks would be conflicted with each other, and the system usually has to make a trade-off among learning all of them together. For many real-world applications where the trade-off has to be made online, multiple models with different preferences over tasks have to be trained and stored. This work proposes a novel controllable Pareto multi-task learning framework, to enable the system to make real-time trade-off control among different tasks with a single model. To be specific, we formulate the MTL as a preference-conditioned multiobjective optimization problem, with a parametric mapping from preferences to the corresponding trade-off solutions. A single hypernetwork-based multi-task neural network is built to learn all tasks with different trade-off preferences among them, where the hypernetwork generates the model parameters conditioned on the preference. For inference, MTL practitioners can easily control the model performance based on different trade-off preferences in real-time. Experiments on different applications demonstrate that the proposed model is efficient for solving various MTL problems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑