In data-rich domains such as vision, language, and speech, deep learning prevails to deliver high-performance task-specific models and can even learn general task-agnostic representations for efficient finetuning to downstream tasks. However, deep learning in resource-limited domains still faces multiple challenges including (i) limited data, (ii) constrained model development cost, and (iii) lack of adequate pre-trained models for effective finetuning. This paper provides an overview of model reprogramming to bridge this gap. Model reprogramming enables resource-efficient cross-domain machine learning by repurposing and reusing a well-developed pre-trained model from a source domain to solve tasks in a target domain without model finetuning, where the source and target domains can be vastly different. In many applications, model reprogramming outperforms transfer learning and training from scratch. This paper elucidates the methodology of model reprogramming, summarizes existing use cases, provides a theoretical explanation of the success of model reprogramming, and concludes with a discussion on open-ended research questions and opportunities. A list of model reprogramming studies is actively maintained and updated at https://github.com/IBM/model-reprogramming.

翻译：在视觉、语言和语音等数据丰富的领域，深度学习通过生成高性能的特定任务模型占据主导地位，甚至能够学习通用的任务无关表征，以便高效地微调到下游任务。然而，资源有限领域的深度学习仍面临多重挑战，包括：(i) 数据有限，(ii) 模型开发成本受限，(iii) 缺乏足够的预训练模型以进行有效微调。本文概述了模型重编程，以弥合这一差距。模型重编程通过重新利用和复用源领域已良好开发的预训练模型，在不进行模型微调的情况下解决目标领域的任务，从而实现资源高效的跨领域机器学习，即使源领域与目标领域差异巨大。在许多应用中，模型重编程优于迁移学习和从零开始训练。本文阐释了模型重编程的方法论，总结了现有的应用案例，提供了模型重编程成功的理论解释，并最后讨论了开放性的研究问题与机遇。模型重编程相关研究的列表正在 https://github.com/IBM/model-reprogramming 上持续维护与更新。