Wenzhe Li

Department of Computer Science
Viterbi School of Engineering
University of Southern California


About Me
I am a 2nd Ph.D student at USC. My research interest includes NLP, deep learning, generative models and its applications to graph-structured data. My current advisor is Aram Galstyan. Before, I was also fortunate to collaborate with Fei Sha (USC), Yan Liu (USC), Max Welling (UvA), Charles Elkan(UCSD) and Tracy Hammond(TAMU). I have couple of years of industry experience working as a full stack software engineer, project lead and chief scientist, and I love solving real-world hard problems.

News!

Our paper on "Scalable Overlapping Community Detection" is selected as the Best Paper Award for IPDPS-Parlearning 2016 !
Our paper on "Scalable MCMC for Mixed Membership Stochastic Blockmodels" is accepted in AISTATS'16
Our paper on "Metric Learning for Ordinal Data" is acceped in AAAI'16

Working Papers

Wenzhe Li, Aram Galstyan, Greg Ver Steeg. Unifying Local and Global Change Detection in Dynamic Network. Under Review.

Ismail EL-Helw, Rutger Hofman, Wenzhe Li, Sungjin Ahn, Max Welling, Henri Bal. Accelerating and Scaling Overlapping Community Detection. Under Review.

Published Full Papers

2017

[Others ]CuiCui Dong, Huifang Du, Yaru Du, Wenzhe Li, Ming Zhao. Path-based learning for plant domain knowledge graph. [Corresponding Author]

[Book Chapter] Zhengping Che, Sanjay Purushotham, DAvid Kale, Wenzhe Li, Mohammad Taha, Robinder Khemani, Yan Liu. Time-Series Feature Learning with Applications to Healthcare Domain. Mobile Health :Sensors, Analytics Methods, and Applications 2017

2016

[IPDPS] EI-Helw, S., Hofman,R., Li, W., Ahn, S., and Welling, M., Bal. H. Scalable Overlapping Community Detection To appear in IPDPS workshop on ParLearning 2016 (Best Paper Award)

[AISTATS] Li, W.*, Ahn, S.*, and Welling, M. Scalable MCMC for Mixed Membership Stochastic Blockmodels To appear in AISTATS'16 [*Equal contribution]

[AAAI] Li, W.*, Shi,Y.* and Sha, F. Metric Learning for Ordinal Data To appear in AAAI'16 [*Equal contribution]

2015

[AMIA] Z. Che*, D. Kale*, M. T. Bahadori,W. Li, and Y. Liu, Causal Phenotype Discovery via Deep Networks in AMIA 2015.

[KDD] Z. Che*, D. Kale*, W. Li, M. T. Bahadori, and Y. Liu, Deep Computational Phenotyping in KDD 2015.

Before 2014

[IAAI] Valentine, S., Vides, F., Lucchese, G., Turner, D., Kim, H. H., Li, W., ... & Hammond, T.. Mechanix: A Sketch-Based Tutoring System for Statics Courses. in IAAI 2012(Innovation Award).

[AI Magazine] Valentine, S., Vides, F., Lucchese, G., Turner, D., Kim, H. H., Li, W. ... & Hammond, T. (2012). Mechanix: A Sketch-Based Tutoring and Grading System for Free-Body Diagrams. AI Magazine 2012, 34(1), 55.

[CHI] Li, W., & Hammond, T. Using scribble gestures to enhance editing behaviors of sketch recognition systems. In CHI'12 Extended Abstracts on Human Factors in Computing Systems 2012 (pp. 2213-2218). ACM.

[AAAI] Li, W., & Hammond, T. A. . Recognizing Text Through Sound Alone. AAAI 2011.


Workshop & Tech Report

An Efficient Approach to Grouping Shapes Using Neighborhood Graphs. Wenzhe Li and Tracy Hammond. Design Computing Cognition (DCC 2012) workshop.

Using scribble gestures to enhance editing behaviors of sketch recognition systems. Wenzhe Li and Tracy Hammond. Design Computing Cognition(DCC 2012) Workshop



Email: wenzheli@usc.edu |
Office: ISI (TBD)