Multi-Objective Reinforced Evolution in Mobile Neural Architecture Search.

Fabricating neural models for a wide range of mobile devices is a challenging task due to highly constrained resources. Recent trends favor neural architecture search involving evolutionary algorithms (EA) and reinforcement learning (RL), however, they are separately used. In this paper, we present a novel multi-objective algorithm called MoreMNAS ( M ulti- O bjective R einforced E volution in M obile N eural A rchitecture S earch) by leveraging good virtues from both sides. Particularly, we devise a variant of multi-objective genetic algorithm NSGA-II, where mutations are performed either by reinforcement learning or a natural mutating process. It maintains a delicate balance between exploration and exploitation . Not only does it prevent the search degradation, but it also makes use of the learned knowledge. Our experiments conducted in Super-resolution domain (SR) deliver rivaling models compared with some state-of-the-art methods at fewer FLOPS (Evaluation code can be found at https://github.com/xiaomi-automl/MoreMNAS ).