AS-NAS: Adaptive Scalable Neural Architecture Search With Reinforced Evolutionary Algorithm for Deep Learning
Tong Zhang, Chunyu Lei, Zongyan Zhang, Xian-Bing Meng, C. L. Philip Chen
Abstract
Neural architecture search (NAS) is a challenging problem in the design of deep learning due to its nonconvexity. To address this problem, an adaptive scalable NAS method (AS-NAS) is proposed based on the reinforced I-Ching divination evolutionary algorithm (IDEA) and variable-architecture encoding strategy. First, unlike the typical reinforcement learning (RL)-based and evolutionary algorithm (EA)-based NAS methods, a simplified RL algorithm is developed and used as the reinforced operator controller to adaptively select the efficient operators of IDEA. Without the complex actor–critic parts, the reinforced IDEA based on simplified RL can enhance the search efficiency of the original EA with lower computational cost. Second, a variable-architecture encoding strategy is proposed to encode neural architecture as a fixed-length binary string. By simultaneously considering variable layers, channels, and connections between different convolution layers, the deep neural architecture can be scalable. Through the integration with the reinforced IDEA and variable-architecture encoding strategy, the design of the deep neural architecture can be adaptively scalable. Finally, the proposed AS-NAS are integrated with the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${L}_{1/2}$ </tex-math></inline-formula> regularization to increase the sparsity of the optimized neural architecture. Experiments and comparisons demonstrate the effectiveness and superiority of the proposed method.