arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.05867cs.LG
收藏

深度学习的可移植性研究综述

Transferability in Deep Learning: A Survey

Tsinghua University(清华大学)

Junguang Jiang, Yang Shu, Jianmin Wang, Mingsheng Long

摘要:

深度学习算法的成功通常取决于大规模数据,而人类似乎具有内在的知识转移能力,通过在遇到和解决未知任务时识别和应用先前学习经验中的相关知识。这种获取和重用知识的能力被称为深度学习中的可转移性。它已经形成了使深度学习像人类学习一样具有数据效率的长期追求,并且一直在激励更强大的深度学习算法的富有成效的设计。我们提出这项调查,以连接深度学习中不同的孤立领域与它们与可移植性的关系,并提供一个统一和完整的视图来调查整个深度学习生命周期的可移植性。该调查详细阐述了基本目标和挑战,以及核心原则和方法,涵盖了深度架构,预培训,任务适应和领域自适应的最新基石。这突出了关于学习可转移知识的适当目标以及使知识适应新的任务和领域、避免灾难性遗忘和负转移的问题。最后,我们实现了一个基准测试和一个开源库,使深度学习方法在可移植性方面得到公平的评估。

英文摘要:

The success of deep learning algorithms generally depends on large-scale data, while humans appear to have inherent ability of knowledge transfer, by recognizing and applying relevant knowledge from previous learning experiences when encountering and solving unseen tasks. Such an ability to acquire and reuse knowledge is known as transferability in deep learning. It has formed the long-term quest towards making deep learning as data-efficient as human learning, and has been motivating fruitful design of more powerful deep learning algorithms. We present this survey to connect different isolated areas in deep learning with their relation to transferability, and to provide a unified and complete view to investigating transferability through the whole lifecycle of deep learning. The survey elaborates the fundamental goals and challenges in parallel with the core principles and methods, covering recent cornerstones in deep architectures, pre-training, task adaptation and domain adaptation. This highlights unanswered questions on the appropriate objectives for learning transferable knowledge and for adapting the knowledge to new tasks and domains, avoiding catastrophic forgetting and negative transfer. Finally, we implement a benchmark and an open-source library, enabling a fair evaluation of deep learning methods in terms of transferability.

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。

↑