Multiple Population Alternate Evolution Neural Architecture Search
Not on the map. Why?
Abstract (arXiv)
The effectiveness of Evolutionary Neural Architecture Search (ENAS) is influenced by the design of the search space. Nevertheless, common methods including the global search space, scalable search space and hierarchical search space have certain limitations. Specifically, the global search space requires a significant amount of computational resources and time, the scalable search space sacrifices the diversity of network structures and the hierarchical search space increases the search cost in exchange for network diversity. To address above limitation, we propose a novel paradigm of searching neural network architectures and design the Multiple Population Alternate Evolution Neural Architecture Search (MPAE), which can achieve module diversity with a smaller search cost. MPAE converts the search space into L interconnected units and sequentially searches the units, then the above search of the entire network be cycled several times to reduce the impact of previous units on subsequent units. To accelerate the population evolution process, we also propose the the population migration mechanism establishes an excellent migration archive and transfers the excellent knowledge and experience in the migration archive to new populations. The proposed method requires only 0.3 GPU days to search a neural network on the CIFAR dataset and achieves the state-of-the-art results.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 37 of its 59 references that are in the map. First posted on arXiv 11 Mar 2024.
Builds on
37 of 59 references.
References · 37
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2013Visualizing and Understanding Convolutional Networkscited by 2,278
- 2019Searching for MobileNetV3cited by 1,984
- 2018DARTS: Differentiable Architecture Searchcited by 1,782
- 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
- 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
- 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,097
- 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 937
- 2018Regularized Evolution for Image Classifier Architecture Searchcited by 902
- 2018Efficient Neural Architecture Search via Parameter Sharingcited by 831
- 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 778
- 2018ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardwarecited by 666
25 more
- 2017Progressive Neural Architecture Searchcited by 483
- 2018FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Searchcited by 480
- 2017Large-Scale Evolution of Image Classifierscited by 348
- 2018SNAS: Stochastic Neural Architecture Searchcited by 288
- 2019Progressive Differentiable Architecture Search: Bridging the Depth Gap between Search and Evaluationcited by 230
- 2017Hierarchical Representations for Efficient Architecture Searchcited by 188
- 2018Efficient Multi-objective Neural Architecture Search via Lamarckian Evolutioncited by 151
- 2019FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Searchcited by 129
- 2017Genetic CNNcited by 124
- 2019Evaluating the Search Phase of Neural Architecture Searchcited by 120
- 2019MixConv: Mixed Depthwise Convolutional Kernelscited by 108
- 2019CARS: Continuous Evolution for Efficient Neural Architecture Searchcited by 79
- 2019One-Shot Neural Architecture Search via Self-Evaluated Template Networkcited by 69
- 2019BayesNAS: A Bayesian Approach for Neural Architecture Searchcited by 67
- 2020NAS-Bench-NLP: Neural Architecture Search Benchmark for Natural Language Processingcited by 60
- 2017Evolving Deep Convolutional Neural Networks for Image Classificationcited by 54
- 2018Automatically designing CNN architectures using genetic algorithm for image classificationcited by 48
- 2018DPP-Net: Device-aware Progressive Search for Pareto-optimal Neural Architecturescited by 40
- 2018BlockQNN: Efficient Block-wise Neural Network Architecture Generationcited by 31
- 2018EA-LSTM: Evolutionary Attention-based LSTM for Time Series Predictioncited by 26
- 2018You Only Search Once: Single Shot Neural Architecture Search via Direct Sparse Optimizationcited by 23
- 2021OPANAS: One-Shot Path Aggregation Network Architecture Search for Object Detectioncited by 19
- 2019Overcoming Multi-Model Forgettingcited by 14
- 2020MUXConv: Information Multiplexing in Convolutional Neural Networkscited by 12
- 2023TS-ENAS:Two-Stage Evolution for Cell-based Network Architecture Searchcited by 1
Built on by
Citing papers per year: 2024: 1.
1 paper.