Education

  • PhD:Georgia Institute of Technology,August 2013 to May 2017
  • Dual-MS:GeorgiaTech-SJTU,August 2010 to May 2013
  • BS:Tianjin University,September 2006 to July 2010

Work Experience

  • Tenure-track Associate Professor: Gaoling School of Artificial Intelligence, Renmin University of China, December 2020 to present
  • Infinia ML Inc., Senior research scientist; Duke University, Visiting researcher,January 2018 to September 2020

RESEARCH INTERESTS

Optimal transport and its application: metric learning, graph analysis and generation, learning for matching and ranking

Point process models: Hawkes process, Markov chain, event sequence analysis

Network analysis and control: Graphon model, social network modeling, network simulation and optimization

Deep learning: Non-real neural networks, high-dimensional dataanalysis and synthesis

Teaching

  • 2021 Fall: Modern Numerical Method, AI-Empowered Medicine and Healthcare

Publications

2020
Gromov-Wasserstein Factorization Models for Graph Clustering
Hongteng Xu
AAAI Conference on Artificial Intelligence (AAAI), 2020.

Learning Autoencoders with Relational Regularization
Hongteng Xu, Dixin Luo, Ricardo Henao, Svati Shah, Lawrence Carin
The International Conference on Machine Learning (ICML), 2020.

2019
Gromov-Wasserstein Learning for Graph Matching and Node Embedding
Hongteng Xu, Dixin Luo, Hongyuan Zha, Lawrence Carin
The International Conference on Machine Learning (ICML), 2019.

Scalable Gromov-Wasserstein Learning for Graph Partitioning and Matching
Hongteng Xu, Dixin Luo, Lawrence Carin
The Conference on Neural Information and Processing System (NeurIPS), 2019.

2018
Online Continuous-Time Tensor Factorization Based on Pairwise Interactive Point Processes,
Hongteng Xu, Dixin Luo, Lawrence Carin
The International Joint Conference on Artificial Intelligence (IJCAI-ECAI), 2018.

Learning Registered Point Processes from Idiosyncratic Observations,
Hongteng Xu, Lawrence Carin, Hongyuan Zha
The International Conference on Machine Learning (ICML), 2018.

Distilled Wasserstein Learning for Word Embedding and Topic Modeling
Hongteng Xu, Wenlin Wang, Wei Liu, Lawrence Carin
The Conference on Neural Information and Processing System (NeurIPS), 2018.

A Unified Framework for Manifold Landmarking
Hongteng Xu, Licheng Yu, Mark Davenport, Hongyuan Zha
IEEE Transactions on Signal Processing (TSP), 2018.

2017
Fractal Dimension Invariant Filtering and Its CNN-based Implementation,
Hongteng Xu, Junchi Yan, Nils Persson, Weiyao Lin and Hongyuan Zha
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2017.

Learning Hawkes Processes from Short Doubly-Censored Event Sequences,
Hongteng Xu, Dixin Luo, Hongyuan Zha
International Conference on Machine Learning (ICML), 2017.

A Dirichlet Mixture Model of Hawkes Processes for Event Sequence Clustering
Hongteng Xu and Hongyuan Zha
Annual Conference on Neural Information Processing Systems (NeurIPS), 2017.

Patient Flow Prediction via Discriminative Learning of Mutually-Correcting Processes
Hongteng Xu, Weichang Wu, Shamim Nemati, Hongyuan Zha
IEEE Transactions on Knowledge and Data Engineering (TKDE), 2017.

2016
Learning Granger Causality for Hawkes Processes,
Hongteng Xu, Mehrdad Farajtabar and Hongyuan Zha
International Conference on Machine Learning (ICML), 2016.

Learning Mixtures of Markov Chains from Aggregate Data with Structural Constraints,
Dixin Luo, Hongteng Xu, Yi Zhen, et al.
IEEE Transactions on Knowledge and Data Engineering (TKDE), 2016.

2015
Dictionary Learning with Mutually Reinforcing Group-Graph Structures,
Hongteng Xu, Licheng Yu, Dixin Luo, Hongyuan Zha, Yi Xu
The Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI), 2015.

Active Manifold Learning via Gershgorin Circle Guided Sample Selection,
Hongteng Xu, Hongyuan Zha, Ren-Cang Li, Mark A. Davenport
The Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI), 2015.

Multi-task Multi-dimensional Hawkes Processes for Modeling Event Sequences,
Hongteng Xu, Dixin Luo, Yi Zhen, Xia Ning, Hongyuan Zha, et al.
The Twenty-fourth International Joint Conference on Artificial Intelligence (IJCAI), 2015.

Trailer Generation via A Point Process-based Visual Attractiveness Model,
Hongteng Xu, Yi Zhen, Hongyuan Zha
The Twenty-fourth International Joint Conference on Artificial Intelligence (IJCAI), 2015.

Unsupervised Trajectory Clustering via Adaptive Multi-Kernel-based Shrinkage,
Hongteng Xu, Yang Zhou, Weiyao Lin and Hongyuan Zha
International Conference on Computer Vision (ICCV), 2015.

2014
Manifold Based Dynamic Texture Synthesis from Extremely Few Samples,
Hongteng Xu, Hongyuan Zha, Mark A. Davenport
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014.

Generalized Equalization Model for Image Enhancement,
Hongteng Xu, Guangtao Zhai, Xiaolin Wu, Xiaokang Yang
IEEE Transactions on Multimedia (TMM), 2014.

2013
Manifold based Image Synthesis from Sparse Samples,
Hongteng Xu, Hongyuan Zha
IEEE Conference on Computer Vision (ICCV), 2013.

Single Image Super-resolution with Detail Enhancement based on Local Fractal Analysis of Gradient,
Hongteng Xu, Guangtao Zhai, Xiaokang Yang
IEEE Transactions on Circuit Systems for Video Technology (CSVT), 2013.

Honors and Awards

  • Coulter Fellowship, Georgia Institute of Technology, 2010

Services

  • Guest Editor:TNNLS
  • Reviewer:TPAMI、TKDE、TIP、TCSVT、TMM、TSP
  • Tutorial:KDD2019
  • Area Chair:ICML2020、ICLR2021、AAAI2021
  • Reviewer:ICML2018-2019、NeurIPS2018-2019、AAAI2017-2020、CVPR2018-2020

Contact

Tel:

Email:hongtengxu@ruc.edu.cn

Website:https://hongtengxu.github.io

Addre: