My name is Dehua Cheng (程德华). I am currently a research scientist at Facebook AI Applied Research, working on the developing cutting-edge machine learning solutions for industry-level personalization problems. Our work ranges from content understanding, large-scale model development, model understanding, AutoML and more.
I graduated with a PhD degree in the Computer Science Department, of University of Southern California. I work on Machine Learning under supervision of Prof. Yan Liu. My primary research interest lies in large scale machine learning. More specifically, I am interested in developing linear or sublinear numerical routines for machine learning algorithms by exploiting randomization and the structures of both the machine learning model and data. I have also worked on parallel inference for probabilistic graphical model, including topic models, Bayesian nonparametrics, etc. And in general, I am interested on (1) designing computational efficient models, and (2) improving existing machine learning algorithms from the computational efficiency aspect. My CV can be found here.
Jan. 2018 - present
Research Scientist
Facebook AI Applied Research.
May 2017 - Aug. 2017
Software Engineer Intern
Feed Machine Learning @ Facebook
Advisor:
Qichao Que
May 2016 - Aug. 2016
Research Intern
Thomas J Watson Research Center
IBM Research
Advisor:
Jie Chen
Aug. 2012 - present
Ph.D.
Computer Science Department
University of Southern California
Advisor:
Yan Liu
Aug. 2008 - Jul. 2012
B.S.
Mathematics and Physics
Tsinghua University
Thesis advisor: Changshui Zhang
Michael Tsang, Dehua Cheng, Hanpeng Liu, Xue Feng, Eric Zhou, and Yan Liu, Feature Interaction Interpretability: A Case for Explaining Ad-Recommendation Systems via Neural Interaction Detection, ICLR 2020.
Geng Ji, Dehua Cheng, Huazhong Ning, Changhe Yuan, Hanning Zhou, Liang Xiong, and Erik B. Sudderth, Variational Training for Large-Scale Noisy-OR Bayesian Networks, UAI 2019.
Michael Tsang, Dehua Cheng, and Yan Liu, Detecting Statistical Interactions from Neural Network Weights, ICLR 2018. [PDF]
Dehua Cheng*, Natali Ruchansky*, and Yan Liu (*Equal Contributions), Matrix completability analysis via graph k-connectivity, AISTATS 2018. [Code]
Dehua Cheng, Richard Peng, Ioakeim Perros, and Yan Liu, SPALS: Fast Alternating Least Squares via Implicit Leverage Scores Sampling, NIPS 2016. [PDF] [Code]
Dehua Cheng, Yu Cheng, Yan Liu, Richard Peng, and Shang-Hua Teng, Efficient Sampling for Gaussian Graphical Models via Spectral Sparsification, COLT 2015. [PDF].
Qi Yu, Dehua Cheng, and Yan Liu, Accelerated Online Low Rank Tensor Learning for Multivariate Spatiotemporal Streams, ICML 2015. [PDF]
Dehua Cheng*, Xinran He*, and Yan Liu (*Equal Contributions), Model Selection for Topic Models via Spectral Decomposition, AISTATS 2015. [PDF]
Dehua Cheng, Mohammad Taha Bahadori, and Yan Liu, FBLG: A Simple and Effective Approach for Temporal Dependence Discovery from Time Series Data, KDD 2014. [PDF]
Dehua Cheng, and Yan Liu, Parallel Gibbs Sampling for Hierarchical Dirichlet Processes via Gamma Processes Equivalence, KDD 2014. [PDF]
Jie Chen, Dehua Cheng, Yan Liu, On Bochner's and Polya's Characterizations of Positive-Definite Kernels and the Respective Random Feature Maps, arXiv:1610.08861
Dehua Cheng, Yu Cheng, Yan Liu, Richard Peng, and Shang-Hua Teng, Spectral Sparsification of Random-Walk Matrix Polynomials, arXiv:1502.03496.
Dehua Cheng, Yu Cheng, Yan Liu, Richard Peng, and Shang-Hua Teng, Scalable Parallel Factorizations of SDD Matrices and Efficient Sampling for Gaussian Graphical Models, arXiv:1410.5392.
Student volunteer, NIPS ’16
Workshop organizer, MiLeTs @ KDD ’16
Student volunteer, ICML ’15
Student volunteer, KDD ’14