论文标题
模型重编程：资源有效的跨域机器学习
Model Reprogramming: Resource-Efficient Cross-Domain Machine Learning
论文作者
论文摘要
在诸如视觉，语言和语音之类的数据范围内，深度学习占上风，可以提供高性能的特定任务模型，甚至可以学习一般任务不合时宜的表示，以进行有效的命名到下游任务。但是，在资源有限的领域中进行深度学习仍然面临着多个挑战，包括（i）数据，（ii）受限的模型开发成本以及（iii）缺乏足够的预培训模型来有效填充。本文概述了模型重编程以弥合此差距。模型重编程可以通过重新利用和重新利用从源域中进行良好发达的预训练的模型来求解资源效率的跨域机器学习，以在不使用模型finetunting的情况下求解目标域中的任务，其中源和目标域可能会大不相同。在许多应用中，模型重编程优于从头开始转移学习和培训。本文阐明了模型重编程的方法，总结了现有用例，提供了对模型重编程成功的理论解释，并在讨论开放式研究问题和机会的讨论中结束了。在https://github.com/ibm/model-proprogramming上积极维护和更新模型重编程研究列表。
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.
