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 the following challenges including (i) limited data, (ii) constrained model development cost, and (iii) lack of adequate pre-trained models for effective finetuning. This paper introduces a new technique called 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 on 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:在诸如愿景、语言和言语等数据丰富的领域,深层次的学习盛行于提供高性能任务特有模型,甚至可以学习一般任务-不可知的表达方式,以便有效地微调下游任务;然而,在资源有限领域的深层次学习仍面临下列挑战,包括:(一) 数据有限,(二) 模型开发成本有限,以及(三) 缺乏适当的预培训模式以进行有效微调。本文介绍了一种称为模型重新规划的新方法,以弥合这一差距。模型重新规划使资源效率高的跨杜梅机学习能够通过重新规划并重新使用来源领域开发的预培训模型,在目标领域解决任务,而不进行模型微调,而资源来源和目标领域可能大不相同。在许多应用中,模型重新规划超出从零开始的转移学习和培训。本文阐述了模型重新规划方法,总结了现有的使用案例,从理论上解释了模型重新规划的成功,并最后对开放式研究问题和机会进行了讨论。模型的更新/模型/模型研究清单正在积极维持。