Automatic Feature Selection By One-Shot Neural Architecture Search In Recommendation Systems

Deep Learning has enabled remarkable progress over the last years on a variety of tasks, such as image recognition, speech recognition, and machine translation. One crucial aspect for this progress are novel neural architectures. Currently employed architectures have mostly been developed manually by human experts, which is a time-consuming and error-prone process. Because of this, there is growing interest in automated neural architecture search methods. We provide an overview of existing work in this field of research and categorize them according to three dimensions: search space, search strategy, and performance estimation strategy. Introduction The success of deep learning in perceptual tasks is largely due to its automation of the feature engineering process: hierarchical feature extractors are learned in an end-to-end fashion from data rather than manually designed. This success has been accompanied, however, by a rising demand for architecture engineering, where increasingly more complex neural architectures are designed manually. Neural Architecture Search (NAS), the process of automating architecture engineering, is thus a logical next step in automating machine learning. NAS can be seen as subfield of AutoML and has significant overlap with hyperparameter optimization and meta-learning (which are described in Chaps. 1 and 2 of this book, respectively). T. Elsken ( )