TY - JOUR AU - Wu, Yan AU - Liu, Aoming AU - Huang, Zhiwu AU - Zhang, Siwei AU - Van Gool, Luc PY - 2021/05/18 Y2 - 2024/03/29 TI - Neural Architecture Search as Sparse Supernet JF - Proceedings of the AAAI Conference on Artificial Intelligence JA - AAAI VL - 35 IS - 12 SE - AAAI Technical Track on Machine Learning V DO - 10.1609/aaai.v35i12.17243 UR - https://ojs.aaai.org/index.php/AAAI/article/view/17243 SP - 10379-10387 AB - This paper aims at enlarging the problem of Neural Architecture Search (NAS) from Single-Path and Multi-Path Search to automated Mixed-Path Search. In particular, we model the NAS problem as a sparse supernet using a new continuous architecture representation with a mixture of sparsity constraints. The sparse supernet enables us to automatically achieve sparsely-mixed paths upon a compact set of nodes. To optimize the proposed sparse supernet, we exploit a hierarchical accelerated proximal gradient algorithm within a bi-level optimization framework. Extensive experiments on Convolutional Neural Network and Recurrent Neural Network search demonstrate that the proposed method is capable of searching for compact, general and powerful neural architectures. ER -