NSGA-Net: Neural Architecture Search using Multi-Objective Genetic Algorithm

Abstract

This paper introduces NSGA-Net -- an evolutionary approach for neural architecture search (NAS). NSGA-Net is designed with three goals in mind: (1) a procedure considering multiple and conflicting objectives, (2) an efficient procedure balancing exploration and exploitation of the space of potential neural network architectures, and (3) a procedure finding a diverse set of trade-off network architectures achieved in a single run. NSGA-Net is a population-based search algorithm that explores a space of potential neural network architectures in three steps, namely, a population initialization step that is based on prior-knowledge from hand-crafted architectures, an exploration step comprising crossover and mutation of architectures, and finally an exploitation step that utilizes the hidden useful knowledge stored in the entire history of evaluated neural architectures in the form of a Bayesian Network. Experimental results suggest that combining the dual objectives of minimizing an error metric and computational complexity, as measured by FLOPs, allows NSGA-Net to find competitive neural architectures. Moreover, NSGA-Net achieves error rate on the CIFAR-10 dataset on par with other state-of-the-art NAS methods while using orders of magnitude less computational resources. These results are encouraging and shows the promise to further use of EC methods in various deep-learning paradigms.

arXiv commentGECCO 2019

References in corpus (16)

• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• An overview of gradient descent optimization algorithms
• Neural Architecture Search with Reinforcement Learning
• Improved Regularization of Convolutional Neural Networks with Cutout
• Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1
• SGDR: Stochastic Gradient Descent with Warm Restarts
• DARTS: Differentiable Architecture Search
• Efficient Neural Architecture Search via Parameter Sharing
• Neural Architecture Optimization
• Designing Neural Network Architectures using Reinforcement Learning
• Efficient Architecture Search by Network Transformation
• XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks
• Neural Architecture Search with Bayesian Optimisation and Optimal Transport
• Progressive Neural Architecture Search
• MONAS: Multi-Objective Neural Architecture Search using Reinforcement Learning
• Reinforced Evolutionary Neural Architecture Search

Cited by in corpus (13)

• Neural Architecture Transfer
• Evaluating the Search Phase of Neural Architecture Search
• Any equation is a forest: Symbolic genetic algorithm for discovering open-form partial differential equations (SGA-PDE)
• Multi-Objective Reinforced Evolution in Mobile Neural Architecture Search
• Contrastive Self-supervised Neural Architecture Search
• How to Train Your Super-Net: An Analysis of Training Heuristics in Weight-Sharing NAS
• Evolutionary Quantum Architecture Search for Parametrized Quantum Circuits
• Modular Grammatical Evolution for the Generation of Artificial Neural Networks
• GreedyNAS: Towards Fast One-Shot NAS with Greedy Supernet
• Powering One-shot Topological NAS with Stabilized Share-parameter Proxy
• Evolving Search Space for Neural Architecture Search
• Regularized Evolutionary Population-Based Training
• An Analysis of Super-Net Heuristics in Weight-Sharing NAS