Jianbo Ye

Machine Learning Researcher and Practitioner, Ph.D.



Bio: Jianbo Ye receives Ph.D. in Information Sciences and Technology, The Pennsylvania State University in 2018. Advised by Prof. James Z. Wang and Prof. Jia Li, Ye developed scalable and robust numerical algorithms of machine learning models that apply optimal transport theory and Wasserstein geometry. He received B.S. degree in Mathematics from University of Science and Technology of China (USTC). He was a research postgraduate at The University of Hong Kong (2011-2012). He has worked as a research intern at Intel (2013) and Adobe (2017). Ye's current research interests include applied machine learning, computational optimal transport, embedded computer vision and affective computing. He is genuinely interested in developing AI solutions for the open world.


What's New

(6-6-2018) 欢迎试用我们基于人工智能和量化建模开发的浙江新高考志愿填报推荐系统桔子高考
(1-31-2018) Penn State News: Jianbo will join Amazon Lab126 as an applied scientist.


Publications

Keywords: all selected optimization learning pattern recognition optimal transport

Journal Publications

Detecting Comma-shaped Clouds for Severe Weather Forecasting using Shape and Motion
Xinye Zheng, Jianbo Ye, Yukun Chen, Stephen Wistar, Jia Li, Jose A. Piedra-Fernández, Michael A. Steinberg, James Z. Wang, IEEE Transactions on Geoscience and Remote Sensing, accepted. (arXiv:1802.08937 [cs.CV], Feb 2018)
pattern recognition

Probabilistic Multigraph Modeling for Improving the Quality of Crowdsourced Affective Data
Jianbo Ye, Jia Li, Michelle G. Newman, Reginald B. Adams, Jr., James Z. Wang, IEEE Transactions on Affective Computing, To appear. (arXiv:1701.01096 [stat.ML], Jan 2017)
DOI g-scholar code dataset learning

This project also develops a scalable data analytic tool, called accelerated D2-clustering, to process large scale distribution data. It could potentially leverage hundreds of CPUs with a very decent scaling efficiency (say, 70-80%).

If you are a government agency, an education institution, or a non-profit organization, we may offer you a FREE academic license of the C/MPI package to run on clusters. Please contact authors by email to discuss details. If you are commercial and would like to use our software, let us know and we will try to arrange to let you use.

Fast Discrete Distribution Clustering Using Wasserstein Barycenter with Sparse Support
Jianbo Ye, Panruo Wu, James Z. Wang and Jia Li, IEEE Transactions on Signal Processing, January 2017 (arXiv:1510.00012 [stat.CO], September 2015)
pdf g-scholar code optimization learning optimal transport


R-BiHDM(-s)[YeYY13], which has been used for SHREC14 human track, is a simple, unsupervised, data independent method. (rank among the best 3 in scanned human dataset)
Shape Retrieval of Non-Rigid 3D Human Models
D. Pickup, et al., International Journal on Computer Vision, April 2016, Springer
pdf g-scholar pattern recognition (benchmark paper, earlier version appeared in EG Workshop 3DOR'14)

A Fast Modal Space Transform For Robust Nonrigid Shape Retrieval
Jianbo Ye and Yizhou Yu, The Visual Computer, March 2015, Springer
pdf g-scholar pattern recognition (extended version of the ICMR'13 paper)

Peer-reviewed Conference Proceedings

2018

A Multi-task Learning Approach for Image Captioning
Wei Zhao, Benyou Wang, Jianbo Ye, Min Yang, Zhou Zhao, Ruotian Luo, Yu Qiao
IJCAI 2018
pdf learning

PLASTIC: Prioritize Long and Short-term Information in Top-n Recommendation using Adversarial Training
Wei Zhao, Benyou Wang, Jianbo Ye, Yongqiang Gao, Min Yang, Xiaojun Chen, Zhou Zhao
IJCAI 2018 (arXiv:1712.09059 [cs.IR], December 2017)
pdf learning

Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layers
Jianbo Ye, Xin Lu, Zhe Lin, and James Z. Wang
ICLR 2018
pdf open review learning optimization

Investigating Active Learning for Concept Prerequisite Learning
Chen Liang, Jianbo Ye, Shuting Wang, Bart Pursel, C. Lee Giles
The AAAI 8th Symposium on Educational Advances in Artifical Intelligence (EAAI), New Orleans, Lousiana, 2018
pdf learning

2017

Dual Learning for Cross-domain Image Captioning
Wei Zhao, Wei Xu, Min Yang, Jianbo Ye, Zhou Zhao, Yabing Feng, and Yu Qiao
CIKM 2017 (Long paper)
pdf g-scholar learning

A Simulated Annealing based Inexact Oracle for Wasserstein Loss Minimization
Jianbo Ye, James Z. Wang and Jia Li
ICML 2017 (arXiv:1608.03859 [stat.CO], August 2016)
pdf & supp g-scholar video optimization learning optimal transport

Determining Gains Acquired from Word Embedding Quantitatively Using Discrete Distribution Clustering
Jianbo Ye, Yanran Li, Zhaohui Wu, James Z. Wang, Wenjie Li, Jia Li
ACL 2017 (Long paper)
pdf g-scholar code dataset learning optimal transport

Recovering Concept Prerequisite Relations From University Course Dependencies
Chen Liang, Jianbo Ye, Zhaohui Wu, Bart Pursel, C. Lee Giles
The AAAI 7th Symposium on Educational Advances in Artifical Intelligence (EAAI), San Francisco, California, 2017
pdf g-scholar dataset preprint learning

2013 ~ 2016

A Distance for HMMs based on Aggregated Wasserstein Metric and State Registration
Yukun Chen, Jianbo Ye, Jia Li
ECCV 2016 (Spotlight Presentation)
pdf g-scholar code pattern recognition optimal transport

Scaling Up Discrete Distribution Clustering Using ADMM
Jianbo Ye and Jia Li
ICIP 2014
pdf g-scholar optimization optimal transport


State-of-the-art unsupervised method to obtain a global nonrigid shape signature for shape retrieval and comparison.
Fast Nonrigid 3D Retrieval Using Modal Space Transform
Jianbo Ye, Zhicheng Yan, and Yizhou Yu
ICMR 2013 (Oral, 17.7% acceptance rate)
pdf g-scholar project page dataset slides pattern recognition

Doctoral Thesis

Jianbo Ye, Computational Modeling of Compositional and Relational Data Using Optimal Transport and Probabilistic Models, Ph.D. thesis, The Pennsylvania State University, May 2018
pdf g-scholar

Preprints

Active Learning of Strict Partial Orders: A Case Study on Concept Prerequisite Relations
Chen Liang, Jianbo Ye, Han Zhao, Bart Pursel, C. Lee Giles
(arXiv:1801:06481 [cs.LG], January 2018)
pdf learning

Investigating Capsule Networks with Dynamic Routing for Text Classification
Wei Zhao, Jianbo Ye, Min Yang, Zeyang Lei, Suofei Zhang, Zhou Zhao
(arXiv:1804.00538 [cs.CL], March 2018)

A Faster Drop-in Implementation for Leaf-wise Exact Greedy Decision Tree Induction Using Pre-sorted Deque
Jianbo Ye
(arXiv:1712.06989 [cs.DS], December 2017)
code learning

Aggregated Wasserstein Metric and State Registration for Hidden Markov Models
Yukun Chen, Jianbo Ye, Jia Li
(arXiv:1711.05792 [cs.LG], November 2017)
pattern recognition optimal transport


Yet another model reduction technique for deformable meshes based on approximation quality controllable subspace.
On the Approximation Theory of Linear Variational Subspace Design
Jianbo Ye and Zhixin Yan
(arXiv:1506.08459 [cs.GR], June 2015)
pdf g-scholar gitxiv software executable demo: linux-x86_64 video (40M) optimization

Presentations

Mar 2018, A Simulated Annealing based Inexact Oracle for Wasserstein Loss Minimization, 42nd SIAM-SEAS Conference, UNC Chapel Hill. slides
Sep 2017, Optimal transport for machine learning: the state-of-the-art numerical tools, Artificial Intelligence Seminar Series, sponsored by Apple, CMU. website
Aug 2017, Oral presentation at ICML, Sydney. video
May 2017, New numerical tools for optimal transport and their machine learning applications BIRS-CMO Workshop (Optimal Transport meets Probability, Statistics and Machine Learning), Oaxaca. video video-2
Oct 2015, Accelerated Discrete Distribution Clustering under Wasserstein Distance
Apr 2014, Probabilistic Graphical Models and Their Applications in Vision and Graphics
Oct 2013, Emerging Technologies in Computer Graphics

Projects outdated

[2015-2016] AD2-Clustering: a parallel clustering algorithm for discrete distributions, including normalized histogram as a special case, under the Wasserstein metric. software (to appear)
C MPI

[2014-2015] neuron: I re-implemented a full-fledged Scala library for composing and training neural network of complex topologies with parameter sharing, supporting different activations, metrics, regularization, and optimization methods. It also includes different variants of multilayer perceptron and auto-encoders. project page
Scala breeze

[2014-2015] dmfCramer: Discrete martrix factorizatin with Cramer risk minimization, which is yet another probabilistic matrix factorization method with loss function based on large deviations theory rather than conventional MLE/MAP framework. project page
Scala breeze

[2013] Pocket Avatar (intern project at Intel): I developed an efficient data-driven framework for real-time facial expression retargeting. demo
C++ MATLAB OpenCV

[2012-2013] iMeshDeform: A C++ mesh deformation framework based on linear variational subspace. project page video
C++ MKL PETSc OpenGL

[2011-2012] R-BiHDM: state-of-the-art, simple and fast signature for nonrigid shapes, which have been tested upon multiple benchmarks. project page
C++ CGAL OpenGL