arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.09796cs.LGcs.CVstat.ML
收藏

基于深度神经网络的多任务学习研究综述

Multi-Task Learning with Deep Neural Networks: A Survey

George Mason University(乔治梅森大学);Department of Computer Science(计算机科学系)

Michael Crawshaw

摘要:

多任务学习(MTL)是机器学习的一个分支,其中多个任务通过共享模型同时学习。这种方法提供了一些优点,例如提高数据效率,通过共享表示减少过拟合,以及通过利用辅助信息快速学习。然而,多个任务的同时学习提出了新的设计和优化挑战,选择哪些任务应该联合学习本身就是一个重要的问题。在本综述中,我们概述了深度神经网络的多任务学习方法,旨在总结该领域内成熟的和最新的方向。我们的讨论是根据现有的深度MTL技术分为三组:架构,优化方法和任务关系学习。我们还提供了常见的多任务基准测试的摘要。

英文摘要:

Multi-task learning (MTL) is a subfield of machine learning in which multiple tasks are simultaneously learned by a shared model. Such approaches offer advantages like improved data efficiency, reduced overfitting through shared representations, and fast learning by leveraging auxiliary information. However, the simultaneous learning of multiple tasks presents new design and optimization challenges, and choosing which tasks should be learned jointly is in itself a non-trivial problem. In this survey, we give an overview of multi-task learning methods for deep neural networks, with the aim of summarizing both the well-established and most recent directions within the field. Our discussion is structured according to a partition of the existing deep MTL techniques into three groups: architectures, optimization methods, and task relationship learning. We also provide a summary of common multi-task benchmarks.

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。

↑