GQNAS: Graph Q Network for Neural Architecture Search

Neural Architecture Search (NAS), aiming to automatically search for neural structure that performs the best, has attracted lots of attentions from both the academy and industry. However, most existing works assume each layer accepts a fixed number of inputs from previous layers, ignoring the flexibility of receiving inputs from an arbitrary number of previous layers. Allowing to receive inputs from an arbitrary number of layers benefits in introducing far more possible combinations of connections among layers, which may also result in much more complex structural relations in architectures. Existing works fail to capture structural correlations among different layers, thus limiting the ability to discover the optimal architecture. To overcome the weakness of existing methods, we study the NAS problem by assuming an arbitrary number of inputs for each layer and capturing the structural correlations among different layers in this paper. Nevertheless, besides the complex structural correlations, considering an arbitrary number of inputs for each layer may also lead to a fully connected structure with up to O(n2) connections for n layers, posing great challenges to efficiently handle polynomial numbers of connections among different layers. To tackle this challenge, we propose a Graph Q Network for NAS (GQNAS), where the states and actions are redefined for searching architectures with input from an arbitrary number of layers. Concretely, we regard a neural architecture as a directed acyclic graph and use graph neural network (GNN) as the Q-function approximation in deep Q network (DQN) to capture the complex structural relations between different layers for obtaining accurate Q-values. Our extensive experiments show that the proposed GQNAS model is able to achieve better performances than several state-of-the-art approaches.

[1]  J. Kwok,et al.  Bridging the Gap between Sample-based and One-shot Neural Architecture Search with BONAS , 2020, NeurIPS.

[2]  Nicholas D. Lane,et al.  BRP-NAS: Prediction-based NAS using GCNs , 2020, NeurIPS.

[3]  Junni Zou,et al.  SI-VDNAS: Semi-Implicit Variational Dropout for Hierarchical One-shot Neural Architecture Search , 2020, IJCAI.

[4]  Mi Zhang,et al.  Does Unsupervised Architecture Representation Learning Help Neural Architecture Search? , 2020, NeurIPS.

[5]  Shaogang Gong,et al.  Neural Graph Embedding for Neural Architecture Search , 2020, AAAI.

[6]  Chang Xu,et al.  CARS: Continuous Evolution for Efficient Neural Architecture Search , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Jian Pei,et al.  AutoNE: Hyperparameter Optimization for Massive Network Embedding , 2019, KDD.

[8]  Lingxi Xie,et al.  PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search , 2019, ICLR.

[9]  Yi Yang,et al.  Searching for a Robust Neural Architecture in Four GPU Hours , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Lihi Zelnik-Manor,et al.  XNAS: Neural Architecture Search with Expert Advice , 2019, NeurIPS.

[11]  Wei-Wei Tu,et al.  Efficient Neural Architecture Search via Proximal Iterations , 2019, AAAI.

[12]  Rongrong Ji,et al.  Multinomial Distribution Learning for Effective Neural Architecture Search , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[13]  Jiaxu Cui,et al.  Deep Neural Architecture Search with Deep Graph Bayesian Optimization , 2019, 2019 IEEE/WIC/ACM International Conference on Web Intelligence (WI).

[14]  Wei Pan,et al.  BayesNAS: A Bayesian Approach for Neural Architecture Search , 2019, ICML.

[15]  Qi Tian,et al.  Progressive Differentiable Architecture Search: Bridging the Depth Gap Between Search and Evaluation , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[16]  Kenneth O. Stanley,et al.  Designing neural networks through neuroevolution , 2019, Nat. Mach. Intell..

[17]  Raquel Urtasun,et al.  Graph HyperNetworks for Neural Architecture Search , 2018, ICLR.

[18]  Liang Lin,et al.  SNAS: Stochastic Neural Architecture Search , 2018, ICLR.

[19]  Tie-Yan Liu,et al.  Neural Architecture Optimization , 2018, NeurIPS.

[20]  Yiming Yang,et al.  DARTS: Differentiable Architecture Search , 2018, ICLR.

[21]  Kirthevasan Kandasamy,et al.  Neural Architecture Search with Bayesian Optimisation and Optimal Transport , 2018, NeurIPS.

[22]  Quoc V. Le,et al.  Efficient Neural Architecture Search via Parameter Sharing , 2018, ICML.

[23]  Alok Aggarwal,et al.  Regularized Evolution for Image Classifier Architecture Search , 2018, AAAI.

[24]  Li Fei-Fei,et al.  Progressive Neural Architecture Search , 2017, ECCV.

[25]  Wei Wu,et al.  Practical Block-Wise Neural Network Architecture Generation , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[26]  Quoc V. Le,et al.  Neural Optimizer Search with Reinforcement Learning , 2017, ICML.

[27]  Vijay Vasudevan,et al.  Learning Transferable Architectures for Scalable Image Recognition , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[28]  Alan L. Yuille,et al.  Genetic CNN , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[29]  Ramesh Raskar,et al.  Designing Neural Network Architectures using Reinforcement Learning , 2016, ICLR.

[30]  Quoc V. Le,et al.  Neural Architecture Search with Reinforcement Learning , 2016, ICLR.

[31]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[32]  Vijay S. Pande,et al.  Molecular graph convolutions: moving beyond fingerprints , 2016, Journal of Computer-Aided Molecular Design.

[33]  Wenwu Zhu,et al.  AutoAttend: Automated Attention Representation Search , 2021, ICML.

[34]  Wenwu Zhu,et al.  Graph Differentiable Architecture Search with Structure Learning , 2021, NeurIPS.

[35]  Wenwu Zhu,et al.  Explainable Automated Graph Representation Learning with Hyperparameter Importance , 2021, ICML.

[36]  Huiqi Li,et al.  Differentiable Neural Architecture Search in Equivalent Space with Exploration Enhancement , 2020, NeurIPS.

[37]  Gaofeng Meng,et al.  DATA: Differentiable ArchiTecture Approximation , 2019, NeurIPS.

[38]  Automated Machine Learning - Methods, Systems, Challenges , 2019, Automated Machine Learning.