Quanming Yao (姚权铭)

Postgradute Student

Department of Computer Science and Engineering

The Hong Kong University of Science and Technology

Clear Water Bay, Kowloon, Hong Kong

E-mail: qyaoaa [AT] cse.ust.hk or quanmingyao [AT] gmail.com

My Github and CV(Feb, 2017)


My Photo

About Me

Hi, I am currently a Ph.D student at Department of Computer Science and Engineering in Hong Kong University of Science and Technology (HKUST), and supervised by Prof. James T. Kwok. I got my bachelor degree at HuaZhong University of Science and Technology (HUST) in 2013. There, I acted as a software consultant of 'Dian Group' for two years, and was a half-year internship at Multi-media and Communication Lab (McLab) doing about image classification. Now, I am working on machine learning, in particular, mainly interested in nonconvex optimization and low-rank modeling. I am a Google Fellowship (machine learning) winner in 2016.

Research Focus

  • Low-rank optimization and modeling.
  • Nonconvex optimization for machine learning.
  • Recommender system.
  • Large-scale machine learning algorithm and system.

Conference Publications  

  1. Huan Zhao, Quanming Yao, James T. Kwok, Dik Lun Lee. Collaborative Filtering with Social Local Models. IEEE International Conference on Data Mining (ICDM-2017), New Orleans, USA, Nov, 2017. (paper)
  2. Huan Zhao, Quanming Yao, Jianda Li, Yangqiu Song, Dik Lun Lee. Meta‐Graph Based Recommendation Fusion over Heterogeneous Information Networks. The 23rd ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD-2017), Halifax, Nova Scotia, Canada, Aug 2017. (paper; code)
  3. Quanming Yao, James T. Kwok. Fei Gao, Wei Chen, Tie-Yan Liu. Efficient Inexact Proximal Gradient Algorithm for Nonconvex Problems. The 26th International Joint Conference on Artificial Intelligence (IJCAI-2017), Melbourne, Australia, Aug 2017. (paper, appendix; code)
  4. Lu Hou, Quanming Yao, James T. Kwok. Loss-aware Binarization of Deep Networks. The 5th International Conference on Learning Representations (ICLR-2017), Palais des Congrès Neptune, Toulon, France, Apr 2017. (paper; code)
  5. Yaqing Wang, James T. Kwok, Quanming Yao, Lionel M. Ni. Zero-Shot Learning with a Partial Set of Observed Attributes. International Joint Conference on Neural Networks (IJCNN-2017), Anchorage, Alaska, USA, May 2017. (paper)
  6. Xiawei Guo, Quanming Yao, James T. Kwok. Efficient Sparse Low-Rank Tensor Completion using Frank-Wolfe Algorithm. The 31st AAAI Conference on Artificial Intelligence (AAAI-2017), San Francisco, CA, USA, Feb 2017. (paper, code)
  7. Quanming Yao, James T. Kwok. Efficient Learning with a Family of Nonconvex Regularizers by Redistributing Nonconvexity. The 33rd International Conference on Machine Learning (ICML-2016), New York City, USA, Jul 2016. (paper, slide, poster; code)
  8. Quanming Yao, James T. Kwok. Greedy Learning of Generalized Low-Rank Models. The 25th International Joint Conference on Artificial Intelligence (IJCAI-2016), New York City, USA, Jul 2016. (paper, appendix, slide)
  9. Quanming Yao, James T. Kwok, Wenliang Zhong. Fast Low-Rank Matrix Learning with Nonconvex Regularization. IEEE International Conference on Data Mining (ICDM-2015), Atlantic City, NJ, USA, Nov 2015. (paper, slide; code)
  10. Quanming Yao, James T. Kwok. Accelerated Inexact Soft-Impute for Fast Large-Scale Matrix Completion. The 24th International Joint Conference on Artificial Intelligence (IJCAI-2015), Buenos Aires, Argentina, Jul 2015. (paper, slide, poster; code)
  11. Quanming Yao, James T. Kwok. Colorization by Patch-Based Local Low-Rank Matrix Completion. The 29th AAAI Conference on Artificial Intelligence (AAAI-2015), Austin, Texas, USA, Jan 2015. (paper, slide)
  12. Quanming Yao, Xiubao Jiang, Mingming Gong, Xingge You, Yu Liu, Duanquan Xu. Efficient Group Learning with Hypergraph Partition in Multi-task Learning. Chinese Conference on Pattern Recognition (CCPR-2012), Beijing, China, Oct 2012. (paper)

Journal Publications  

  1. Yi Yang, Quanming Yao, Huamin Qu. VISTopic: A Visual Analytics System for Making Sense of Large Document Collections using Hierarchical Topic Modeling. Journal of Visual Informatics, 2017. (paper)

Awards

  • Google PhD Fellowship in Machine Learning (13 students in worldwide, 2016)
  • Travel Grant: IJCAI 2015, ICML 2016
  • Tse Cheuk Ng Tai Research Excellence Prize (HKUST, 2014-2015)
  • Excellent Bachelor Thesis, 'Large Scale Image Classification' (1st class, HuBei Province, 2013)
  • Qiming Star (5/40000, HUST, 2012)
  • National Scholarship (5/300, HUST, 2012)

Working Experience

Talks & Presentations

  • Some Thoughts on Algorithms for Machine Learning. 15th Anniversary of Dian Group, HUST (Wuhan). 28/05/2017
  • Optimization for Machine Learning - with a focus on proximal gradient descent algorithm. 4Paradigm (Beijing). 24/02/2017 (slides)
  • Efficient Learning with Nonconvex Regularizers by Redistributing Nonconvexity. McLab, HUST (Wuhan). 27/09/2016
  • Fast Learning with Nonconvex Regularization. NLP Department, Baidu (Shenzhen). 21/07/2016
  • Low-Rank Modeling with Fast Optimization. Citadel (Hong Kong). 31/03/2016

Academic Service

  • Conference Reviewer: NIPS 2017, ICML 2017, AAAI 2017, NIPS 2016, AAAI 2016.
  • Journal Reviewer: IEEE/ACM Transaction on Networking, IEEE Journal of Biomedical and Health Informatics

Teaching Assistant

  • COMP 4331: Introduction to Data Mining. (Spring 2015)
  • COMP 1022: Excel VBA Programming. (Fall 2014)

Study Notes

  • ADMM - An usage study. 04/2017. (slides)
  • Proximal Gradient Descent Algorithm - A quick guidance. 03/2017. (handouts)
  • Optimization Approaches for Learning with Low-rank Regularization. 10/2016. (PQE survey, slides).
  • A Comparison on Algorithms for Learning with Nonconvex Regularization (with Yongqi Zhang). 11/2015. (draft).
  • Convergence analysis of pupular optimization algorithms. 10/2014. (gradient descent, proximal gradient descent).