Quantum semi-supervised generative adversarial network for enhanced data classification

In this paper, we propose the quantum semi-supervised generative adversarial network (qSGAN). The system is composed of a quantum generator and a classical discriminator/classifier (D/C). The goal is to train both the generator and the D/C, so that the latter may get a high classification accuracy for a given dataset. The generator needs neither any data loading nor to generate a pure quantum state, while it is expected to serve as a stronger adversary than a classical one thanks to its rich expressibility. These advantages are demonstrated in a numerical simulation.

[1]  Ji-Rong Wen,et al.  PSGAN: A Minimax Game for Personalized Search with Limited and Noisy Click Data , 2019, SIGIR.

[2]  Abhinav Anand,et al.  Experimental demonstration of a quantum generative adversarial network for continuous distributions , 2020, ArXiv.

[3]  Daniel Herr,et al.  Anomaly detection with variational quantum generative adversarial networks , 2020, Quantum Science and Technology.

[4]  Kristan Temme,et al.  Supervised learning with quantum-enhanced feature spaces , 2018, Nature.

[5]  Seth Lloyd,et al.  Quantum Generative Adversarial Learning. , 2018, Physical review letters.

[6]  Stefan Woerner,et al.  Quantum Generative Adversarial Networks for learning and loading random distributions , 2019, npj Quantum Information.

[7]  Peng Zhang,et al.  IRGAN: A Minimax Game for Unifying Generative and Discriminative Information Retrieval Models , 2017, SIGIR.

[8]  Alexei A. Efros,et al.  Generative Visual Manipulation on the Natural Image Manifold , 2016, ECCV.

[9]  Fan Yang,et al.  Good Semi-supervised Learning That Requires a Bad GAN , 2017, NIPS.

[10]  Ashley Montanaro,et al.  Achieving quantum supremacy with sparse and noisy commuting quantum computations , 2016, 1610.01808.

[11]  Simone Severini,et al.  Quantum machine learning: a classical perspective , 2017, Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[12]  Seth Lloyd,et al.  Quantum random access memory. , 2007, Physical review letters.

[13]  Jiahai Wang,et al.  CatGAN: Category-aware Generative Adversarial Networks with Hierarchical Evolutionary Learning for Category Text Generation , 2019, AAAI.

[14]  Lei Wang,et al.  Differentiable Learning of Quantum Circuit Born Machine , 2018, Physical Review A.

[15]  Shenggen Zheng,et al.  Quantum generative adversarial network for generating discrete data , 2018 .

[16]  Dacheng Tao,et al.  Experimental Quantum Generative Adversarial Networks for Image Generation , 2020, Physical Review Applied.

[17]  Francesco Petruccione,et al.  Quantum classifier with tailored quantum kernel , 2019 .

[18]  Ievgeniia Oshurko Quantum Machine Learning , 2020, Quantum Computing.

[19]  Shin Ishii,et al.  Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  Yongqiang Zhang,et al.  SOD-MTGAN: Small Object Detection via Multi-Task Generative Adversarial Network , 2018, ECCV.

[21]  Holger H. Hoos,et al.  A survey on semi-supervised learning , 2019, Machine Learning.

[22]  Franco Nori,et al.  Quantum State Tomography with Conditional Generative Adversarial Networks , 2020, Physical review letters.

[23]  R. Jozsa,et al.  Classical simulation of commuting quantum computations implies collapse of the polynomial hierarchy , 2010, Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[24]  Xiaoming Liu,et al.  Representation Learning by Rotating Your Faces , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[25]  Simone Severini,et al.  Adversarial quantum circuit learning for pure state approximation , 2018, New Journal of Physics.

[26]  David M. Reif,et al.  Leveraging high-throughput screening data, deep neural networks, and conditional generative adversarial networks to advance predictive toxicology , 2021, PLoS Comput. Biol..

[27]  Junmei Wang,et al.  Deep convolutional generative adversarial network (dcGAN) models for screening and design of small molecules targeting cannabinoid receptors. , 2019, Molecular pharmaceutics.

[28]  M. Schuld,et al.  Prediction by linear regression on a quantum computer , 2016, 1601.07823.

[29]  Yu Qiao,et al.  ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks , 2018, ECCV Workshops.

[30]  Augustus Odena,et al.  Semi-Supervised Learning with Generative Adversarial Networks , 2016, ArXiv.

[31]  A. Harrow,et al.  Quantum Supremacy through the Quantum Approximate Optimization Algorithm , 2016, 1602.07674.

[32]  Philippe Thomas Review of Semi-supervised learning by O. Chapelle, B. Schölkopf, and A. Zien, Eds. London, UK, MIT Press, 2006 , 2009 .

[33]  Shu-Hao Wu,et al.  Quantum generative adversarial learning in a superconducting quantum circuit , 2018, Science Advances.

[34]  Byron Boots,et al.  Learning and Inference in Hilbert Space with Quantum Graphical Models , 2018, NeurIPS.

[35]  Zhenan Sun,et al.  A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications , 2020, IEEE Transactions on Knowledge and Data Engineering.

[36]  Wojciech Zaremba,et al.  Improved Techniques for Training GANs , 2016, NIPS.

[37]  Ashley Montanaro,et al.  Average-case complexity versus approximate simulation of commuting quantum computations , 2015, Physical review letters.

[38]  Ruili Wang,et al.  Image Synthesis with Adversarial Networks: a Comprehensive Survey and Case Studies , 2020, Inf. Fusion.

[39]  Sergey Nikolenko,et al.  druGAN: An Advanced Generative Adversarial Autoencoder Model for de Novo Generation of New Molecules with Desired Molecular Properties in Silico. , 2017, Molecular pharmaceutics.

[40]  Shouvanik Chakrabarti,et al.  Quantum Wasserstein Generative Adversarial Networks , 2019, NeurIPS.

[41]  Travis S. Humble,et al.  Quantum supremacy using a programmable superconducting processor , 2019, Nature.

[42]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[43]  Matteo A. C. Rossi,et al.  IBM Q Experience as a versatile experimental testbed for simulating open quantum systems , 2019, npj Quantum Information.

[44]  Natalia Gimelshein,et al.  PyTorch: An Imperative Style, High-Performance Deep Learning Library , 2019, NeurIPS.

[45]  Alan Aspuru-Guzik,et al.  Variational Quantum Generators: Generative Adversarial Quantum Machine Learning for Continuous Distributions , 2019, Advanced Quantum Technologies.

[46]  Sebastian Thrun,et al.  Text Classification from Labeled and Unlabeled Documents using EM , 2000, Machine Learning.

[47]  Nathan Killoran,et al.  Quantum generative adversarial networks , 2018, Physical Review A.

[48]  Chuan Li,et al.  Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks , 2016, ECCV.

[49]  Jiangping Hu,et al.  Learning and Inference on Generative Adversarial Quantum Circuits , 2018, Physical Review A.

[50]  Masanao Ozawa,et al.  Soundness and completeness of quantum root-mean-square errors , 2018, npj Quantum Information.

[51]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[52]  M. Schuld,et al.  Circuit-centric quantum classifiers , 2018, Physical Review A.

[53]  Jacob biamonte,et al.  Quantum machine learning , 2016, Nature.

[54]  Kai Xu,et al.  Quantum generative adversarial networks with multiple superconducting qubits , 2020, npj Quantum Information.

[55]  Eugene Lin,et al.  Relevant Applications of Generative Adversarial Networks in Drug Design and Discovery: Molecular De Novo Design, Dimensionality Reduction, and De Novo Peptide and Protein Design , 2020, Molecules.