Qibin Zhao

Unit leader at Tensor Learning Unit (TLU), RIKEN Center for Advanced Intelligence Project (AIP).
Email: qibin.zhao [at] riken.jp

Tensor Learning Unit

We study various tensor-based machine learning technologies, e.g., tensor decomposition, multilinear latent variable model, tensor regression and classification, tensor networks, deep tensor learning, and Bayesian tensor learning, with aim to facilitate the learning from high-order structured data or large-scale latent space. Our goal is to develop innovative, scalable and efficient tensor learning algorithms supported by theoretical principles. The novel applications in computer vision and brain data analysis will also be explored to provide new insights into tensor learning methods.


News

  • 11. 2018     Our paper has been accepted to AAAI 2019.

  • 10. 2018     Unit Leader Qibin Zhao talked at International Workshop on Tensor Networks and Machine Learning, Skoltech, Moscow.

  • 06. 2018     Dr. Guillaume Rabusseau (McGill University, Canada) give a talk "Machine Learning with Tensors for Structured Data".

  • 06. 2018     Lecture at Waseda University. [Silde]

  • 05. 2018     Prof. Danilo Mandic (Imperial College London, UK) give a talk "Hearables: Enabling technologies for lifelong learning in E-Health".

  • 04. 2018     Our paper has been accepted to IJCAI 2018.

  • 03. 2018     Prof. Justin Dauwels (Nanyang Technological University, Singapore) give a talk "Bayesian Inference of Sparse Networks (BISN)".

  • 01. 2018     Our paper has been accepted to ICLR 2018 (Workshop).

  • 01. 2018     Our paper has been accepted to ICASSP 2018.

  • 12. 2017     Dr. Fabien Lotte (Inria Bordeaux Sud-Ouest, France) give a talk "Combining machine learning and psychology to design usable Brain-Computer Interfaces".

  • 12. 2017     Dr. Tomasz M. RUTKOWSKI (Cogent Labs Inc., The University of Tokyo, Japan) give a talk "End-to-end Deep-learning Approaches for Online BCI and Offline Experiment Brainwave Analyses".

  • Members

    Unit Leader

    Qibin Zhao

    Postdoctoral Researcher

          
    Ming Hou           Chao Li

    Parttimer

                 
    Longhao Yuan   Xuyang Zhao

    Intern


    Visiting Scientist

    Andrzej Cichocki,   Toshihisa Tanaka,   Jianting Cao,   Cesar F. Caiafa,   Jordi Solé-Casals

    Visitor

    Prof. Brahim CHAIB-DRAA,   Dr. Tomasz M. RUTKOWSKI,   Dr. Fabien Lotte,   Prof. Justin Dauwels,
    Prof. Danilo Mandic,   Dr. Guillaume Rabusseau

    Former members

    Jinshi Yu (Intern),   Anjie Zhang (Parttimer),   Xingwei Cao (Parttimer),   Shifeng Huang (Intern),
    Xinqi Chen (Intern)

    Publications

    Conference

    2019
    • X. Kong, W. Kong, Q. Fan, Q. Zhao, and A. Cichocki. 2019, “Task-independent EEG identification via low-rank matrix decomposition,” in The IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pp. 412–419.

    • L. Yuan, C. Li, M. Danilo, J. Cao, and Q. Zhao. 2019, “Tensor ring decomposition with rank minimization on latent space: An efficient approach for tensor completion,” in The Thirty-Third AAAI Conference on Artificial Intelligence (AAAI-19). [Code]

    2018
    • X. Cao, X. Zhao, and Q. Zhao. 2018, “Tensorizing generative adversarial nets,” in The Third International Conference On Consumer Electronics (ICCE) Asia, pp. 206–212. [Paper] [Code]

    • M. Hou, B. Chaib-draa, C. Li, and Q. Zhao. 2018, “Generative adversarial positive-unlabeled learning,” in Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI-18), pp. 2255–2261. [Paper] [Silde] [Code]

    • T. M. Rutkowski, Q. Zhao, M. S. Abe, and M. Otake. 2018, “AI neurotechnology for ag- ing societies–task-load and dementia EEG digital biomarker development using information geometry machine learning methods,” in NeurIPS Workshop.

    • J. Yu, G. Zhou, Q. Zhao, and K. Xie. 2018, “An effective tensor completion method based on multi-linear tensor ring decomposition,” in APSIPA-ASC 2018, pp. 1244–1349. [Paper]

    • L. Yuan, J. Cao, X. Zhao, Q. Wu, and Q. Zhao. 2018, “Higher-dimension tensor completion via low-rank tensor ring decomposition,” in APSIPA-ASC 2018, pp. 1071–1076. [Paper]

    • L. Yuan, Q. Zhao, and J. Cao. 2018, “High-order tensor completion for data recovery via sparse tensor-train optimization,” in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1258–1262. [Paper]

    • Q. Zhao, M. Sugiyama, L. Yuan, and A. Cichocki. 2018, “Learning efficient tensor representa- tions with ring structure networks,” in Sixth International Conference on Learning Represen- tations (ICLR Workshop). [Paper]

    • X. Zhao, T. Tanaka, W. Kong, Q. Zhao, J. Cao, H. Sugano, and N. Yoshida. 2018, “Epileptic focus localization based on iEEG by using positive unlabeled (PU) learning,” in APSIPA-ASC 2018, pp. 493–497. [Paper]

    • X. Zhao, Q. Zhao, T. Tanaka, J. Cao, W. Kong, H. Sugano, and N. Yoshida. 2018, “Detection of epileptic foci based on interictal iEEG by using convolutional neural network,” in The 23rd International Conference on Digital Signal Processing (DSP).

    • X. Zhao, G. Cui, L. Yuan, T. Tanaka, Q. Zhao, and J. Cao. 2018, “A hybrid brain com- puter interface based on audiovisual stimuli p300,” in The Third International Conference On Consumer Electronics (ICCE) Asia, pp. 206–212. [Paper]
    2017
    • G. Cui, L. Zhu, Q. Zhao, J. Cao, and A. Cichocki. 2017, “A graph theory analysis on distin- guishing EEG-based brain death and coma,” in International Conference on Neural Information Processing (ICONIP), ser. Lecture Notes in Computer Science, Springer, vol. 10637, pp. 589– 595. [Paper]

    • L. Gui, G. Cui, Q. Zhao, D. Wang, A. Cichocki, and J. Cao. 2017, “Video denoising using low rank tensor decomposition,” in Ninth International Conference on Machine Vision (ICMV 2016), International Society for Optics and Photonics, vol. 10341, p. 103410V. [Paper]

    • L. Gui, Q. Zhao, and J. Cao. 2017, “Brain image completion by Bayesian tensor decomposi- tion,” in Proceedings of 22nd International Conference on Digital Signal Processing (DSP),, IEEE, pp. 1–4. [Paper]

    • Q. Shi, Y.-m. Cheung, and Q. Zhao. 2017, “Feature extraction for incomplete data via low- rank Tucker decomposition,” in Joint European Conference on Machine Learning and Knowl- edge Discovery in Databases (ECML PKDD), ser. Lecture Notes in Computer Science, IEEE, vol. 10534, pp. 564–581. [Paper]

    • Y. Xin, Q. Wu, Q. Zhao, and Q. Wu. 2017, “Semi-supervised regularized discriminant analysis for EEG-based BCI system,” in International Conference on Intelligent Data Engineering and Automated Learning (IDEAL), Springer, pp. 516–523. [Paper]

    • L. Yuan, Q. Zhao, and J. Cao. 2017, “Completion of high order tensor data with missing entries via tensor-train decomposition,” in International Conference on Neural Information Processing (ICONIP), ser. Lecture Notes in Computer Science, Springer, vol. 10634, pp. 222–229. [Paper]

    Journal

    2018
    • L. Gui, X. Zhao, Q. Zhao, and J. Cao. 2018, “Image and video completion by using Bayesian tensor decomposition,” International Journal of Computer Science Issues (IJCSI), vol. 15, no. 5, pp. 1–8. [Paper]

    • L. Gui, X. Zhao, Q. Zhao, and J. Cao. 2018, “Non-local image denoising by using Bayesian low- rank tensor factorization on high-order patches,” International Journal of Computer Science Issues (IJCSI), vol. 15, no. 5, pp. 16–25. [Paper]

    • W. Kong, L. Wang, J. Zhang, Q. Zhao, and J. Sun. 2018, “The dynamic EEG microstates in mental rotation,” Sensors, vol. 18, no. 9, p. 2920. [Paper]

    • Y. Kumagai, R. Matsui, and T. Tanaka. 2018, “Music familiarity affects EEG entrainment when little attention is paid,” Frontiers in Human Neuroscience, vol. 12, p. 444. [Paper]

    • J. Lin, W. Chen, C. Shen, M. Chiu, Y. Kao, F. Lai, Q. Zhao, and A. Cichocki. 2018, “Visualization and sonification of long-term epilepsy electroencephalogram monitoring,” Journal of Medical and Biological Engineering, vol. 38, no. 6, pp. 943–952. [Paper]

    • Q. Shi, Y. Cheung, Q. Zhao, and H. Lu. 2018, “Feature extraction for incomplete data via low- rank tensor decomposition with feature regularization,” IEEE Transactions on Neural Networks and Learning Systems (TNNLS). [Paper]

    • J. Sol ́e-Casals, C. F. Caiafa, Q. Zhao, and A. Cichocki. 2018, “Brain-computer interface with corrupted EEG data: A tensor completion approach,” Cognitive Computation, vol. 10, no. 6, pp. 1062–1074. [Paper]

    • L. Yuan, Q. Zhao, L. Gui, and J. Cao. 2018, “High-order tensor completion via gradient-based optimization under tensor train format,” Signal Processing: Image Communication. [Paper]

    • Y. Zhang, D. Guo, and F. Li, et al. 2018, “Correction to “correlated component analysis for enhancing the performance of SSVEP-based brain-computer interface”,” IEEE Transactions on Neural Systems and Rehabilitation Engineering (TNSRE), vol. 26, no. 8, pp. 1645–1646. [Paper]

    • Y. Zhang, E. Yin, F. Li, Y. Zhang, T. Tanaka, Q. Zhao, Y. Cui, P. Xu, D. Yao, and D. Guo. 2018, “Two-stage frequency recognition method based on correlated component analysis for SSVEP-based BCI,” IEEE Transactions on Neural Systems and Rehabilitation Engineering (TNSRE), vol. 26, no. 7, pp. 1314–1323, issn: 1534-4320. [Paper]

    • Y. Zhang, D. Guo, F. Li, E. Yin, Y. Zhang, P. Li, Q. Zhao, T. Tanaka, D. Yao, and P. Xu. 2018, “Correlated component analysis for enhancing the performance of SSVEP-based brain- computer interface.,” IEEE Transactions on Neural Systems and Rehabilitation Engineering (TNSRE), vol. 26, no. 5, pp. 948–956. [Paper]

    Book

    • A. Cichocki, A.-H. Phan, Q. Zhao, N. Lee, I. Oseledets, M. Sugiyama, D. P. Mandic et al., “Tensor networks for dimensionality reduction and large-scale optimization: Part 2 applications and future perspectives,” Foundations and Trends R in Machine Learning, vol. 9, no. 6, pp. 431-673, 2017. [Book]

    • A. Cichocki, N. Lee, I. Oseledets, A.-H. Phan, Q. Zhao, D. P. Mandic et al., “Tensor networks for dimensionality reduction and large-scale optimization: Part 1 low-rank tensor decompositions,” Foundations and Trends R in Machine Learning, vol. 9, no. 4-5, pp. 249-429, 2016. [Book]

    Softwares

    • TRLRF: Tensor Ring Low-rank Factors (Matlab) [Github]
    • TGAN: Tensorizing Generative Adversarial Nets (Python) [Github]
    • Gan PU: Generative Adversarial Positive-Unlabeled Learning (Python) [Code]
    • FBCP: Bayesian CP Factorization for Tensor Completion (Matlab) [Github]
    • BRTF: Bayesian Robust Tensor Factorization (Matlab) [Github]
    • T3C: Tensor-Train Tensor Completion (Matlab) [Github]

    Sildes

    • IJCAI 18: Generative Adversarial Positive-unlabeled Learning [Silde]
    • Waseda University Lectures
    • Lecture 1: Multilinear Algebra and Tensor Decompositions [Silde]
      Lecture 2: Tensor Networks [Silde]
      Lecture 3: Tensor Methods for Signal Processing and Machine Learning [Silde]

    Access

    Access to Center for Advanced Intelligence Project

    RIKEN Center for Advanced Intelligence Project,
    Nihonbashi 1-chome Mitsui Building, 15th floor,
    1-4-1 Nihonbashi, Chuo-ku, Tokyo.
    〒103-0027, Japan.
    Tel: +81-(0)48-467-3626


    Job Opportunities

    Seeking Openings for Research Scientists or Postdoctoral Researchers or Technical Scientist or Internship Student. [Job]

    Copyright Tensor Learning Unit, All rights reserved.