Proceedings of the Genetic and Evolutionary Computation Conference Companion · 2022 · 17 citations · 3 references
ComputingComputer EngineeringComputer ScienceArtificial IntelligenceComputer VisionMachine LearningDeep LearningEvolutionary ComputationEvolutionary OptimizationGenetic AlgorithmsMetaheuristic OptimizationPopulation-based SearchArchitecture ExplorationArchitecture SearchEvolutionary SearchGuided Local SearchMutationNeural Architecture Search
Neural Architecture Search methods have been successfully applied to image tasks with excellent results. However, NAS methods are often complex and tend to quickly converge for local minimas. In this paper, we propose G-EA, a novel approach for guided NAS. G-EA guides the evolution by exploring the search space by generating and evaluating several architectures in each generation at initialisation stage using a zero-proxy estimator, where only the highest-scoring architecture is trained and kept for the next generation. By generating several off-springs from an existing architecture at each generation, G-EA continuously extracts knowledge about the search space without added complexity. More, G-EA forces exploitation of the most performant architectures by descendant generation while at the same time forcing exploration by parent mutation and favouring younger architectures to the detriment of older ones. Experimental results demonstrate the effectiveness of the proposed method. Results show that G-EA achieves state-of-the-art results in NAS-Bench-101 and in all NAS-Bench-201 search space data sets: CIFAR-10, CIFAR-100 and ImageNet16-120, with mean accuracies of 93.99%, 72.62% and 46.04% respectively.
3
Searching for a Robust Neural Architecture in Four GPU Hours
Xuanyi Dong, Yi Yang · 2019 · 679 citations · Full text
Practical Block-Wise Neural Network Architecture Generation
Zhao Zhong, Junjie Yan, Wei Wu et al. · 2018 · 539 citations
One-Shot Neural Architecture Search via Self-Evaluated Template Network
Xuanyi Dong, Yi Yang · 2019 · 207 citations · Full text