A portrait of Bert Huang

Bert Huang

Assistant Professor of Computer Science

bhuang@vt.edu

About Me

I am an assistant professor in the Virginia Tech Department of Computer Science. I investigate machine learning with a special focus on models and data with structure stemming from natural networks. Within this focus, my work addresses open questions on theory, algorithms, and applications.

A note for prospective students.

News

  • I'll be teaching Advanced Machine Learning/Machine Learning in the fall. This is an introductory course in machine learning, despite its name (we're working on fixing the name).
  • We're running a workshop on cybersafety at WWW 2017. Come discuss how computing can help make the Web safer. CyberSafety 2017.
  • I'll be speaking at the First ACM International Workshop on Computational Methods for Cybersafety, co-located with CIKM16.
  • Our paper Hinge-Loss Markov Random Fields and Probabilistic Soft Logic by Stephen H. Bach, Matthias Broecheler, me, and Lise Getoor was accepted and will appear in the Journal of Machine Learning Research!
  • Shuangfei Fan will be presenting our paper at the Workshop on Mining and Learning with Graphs on using back-propagation for learning collected classifiers. Come see her poster!
  • Elaheh Raisi and I will be presenting a paper on cyberbullying detection at the ICML workshop #Data4Good. See you in NYC!
  • Our paper Stability and Generalization in Structured Prediction by Ben London, me, and Lise Getoor was accepted and will appear in the Journal of Machine Learning Research!
An image of a graph

Research

Machine Learning Laboratory

I direct the Machine Learning Laboratory. We investigate the problem of machine learning for complex phenomena. We focus on rich settings where data is best modeled as multi-relational, multi-modal networks. We emphasize the joint exploration of theoretical, algorithmic, and applied research and aim to exploit connections within these views to strengthen understanding of each.

Picture of the Machine Learning Laboratory from Fall 2016

Graduate Students

Walid Chaabene
Shuangfei Fan
Elaheh Raisi
Sirui Yao

General Information

Curriculum Vitae
BibTeX Listing
Google Scholar Author Page

2017

Recurrent Collective Classification
S. Fan, B. Huang. International Conference on Network Science (NetSci) and Satellite Symposium on Machine Learning in Network Science 2017.
Abstract

Detecting Cyber Bullying: But Can it Be Stopped?
Robbie Harris, WVTF Public Radio Interview.
Radio Interview

Virginia Tech professor builds algorithm to detect traces of cyberbullying
Izzy Rossi, News Editor, Collegiate Times.
Press Article

Dispelling five common myths about cyberbullying
Ceci Leonard, Media Relations, Virginia Tech.
Press Article

2016

A Weakly Supervised Approach for Adaptive Detection of Cyberbullying Roles
B. Huang. Workshop on Computational Methods for CyberSafety. Invited talk.
Abstract

Training Iterative Collective Classifiers with Back-Propagation
S. Fan, B. Huang. Workshop on Mining and Learning with Graphs.
Paper

Cyberbullying Identification Using Participant-Vocabulary Consistency
E. Raisi, B. Huang. #Data4Good: Machine Learning in Social Good Applications. ICML 2016 workshop.
Paper

Stability and Generalization in Structured Prediction
B. London, B. Huang, L. Getoor. Journal of Machine Learning Research. To appear.
Preprint

Machine Learning for Detecting Detrimental Online Social Behavior
B. Huang, E. Raisi. Computing Community Consortium (CCC) Symposium on Computing Research: Addressing National Priorities and Societal Needs.
Video, Poster, CCCBlog post

Capturing Planned Protests from Open Source Indicators
S. Muthiah, B. Huang, J. Arredondo, D. Mares, L. Getoor, G. Katz, N. Ramakrishnan. Artificial Intelligence Magazine.
Paper

2015

Paired-Dual Learning for Training Hinge-Loss MRFs with Latent Variables
S. Bach, B. Huang, J. Boyd-Graber, L. Getoor. International Conference on Machine Learning (ICML) 2015.
Paper, Talk

The Benefits of Learning with Strongly Convex Approximate Inference
B. London, B. Huang, L. Getoor. International Conference on Machine Learning (ICML) 2015
Paper, Talk

Paired-Dual Learning for Circumventing the Inference Bottleneck
B. Huang. New Perspectives on Relational Learning, Banff International Research Station for Mathematical Innovation and Discovery
Talk

Joint Models of Disagreement and Stance in Online Debate
D. Sridhar, J. Foulds, M. Walker, B. Huang, L. Getoor. Annual Meeting of the Association for Computational Linguistics (ACL) 2015
Paper

Unifying Local Consistency and MAX SAT Relaxations for Scalable Inference with Rounding Guarantees
S. Bach, B. Huang, L. Getoor. International Conference on Artificial Intelligence and Statistics (AISTATS) 2015
Paper

Planned Protest Modeling in News and Social Media
S. Muthiah, B. Huang, J. Arredondo, D. Mares, L. Getoor, G. Katz, N. Ramakrishnan. Conference on Innovative Applications of Artificial Intelligence (IAAI) 2015. Deployed Application Award.
Paper

2014

Network-Based Drug-Target Interaction Prediction with Probabilistic Soft Logic
S. Fakhraei, B. Huang, L. Raschid, L. Getoor. IEEE/ACM Transactions on Computational Biology and Bioinformatics.
Paper

Discovering Evolving Political Vocabulary in Social Media
A. Mahendiran, W. Wang, J. Arredondo, B. Huang, L. Getoor, D. Mares, N. Ramakrishnan. International Conference on Behavioral, Economic, and Socio-Cultural Computing (BESC) 2014.
Paper

“Beating the News” With EMBERS: Forecasting Civil Unrest Using Open Source Indicators
N. Ramakrishnan, P. Butler, N. Self, R. Khandpur, P. Saraf, W. Wang, J. Cadena, A. Vullikanti, G. Korkmaz, C. Kuhlman, A. Marathe, L. Zhao, H. Ting, B. Huang, A. Srinivasan, K. Trinh, L. Getoor, G. Katz, A. Doyle, C. Ackermann, I. Zavorin, J. Ford, K. Summers, Y. Fayed, J. Arredondo, D. Gupta, D. Mares. ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) 2014.
Paper

Learning Latent Engagement Patterns of Students in Online Courses
A. Ramesh, D. Goldwasser, B. Huang, H. Daumé III, L. Getoor. AAAI Conference on Artificial Intelligence 2014.
Paper

PAC-Bayesian Collective Stability
B. London, B. Huang, and L. Getoor. International Conference on Artificial Intelligence and Statistics (AISTATS) 2014.
Paper

Rounding Guarantees for Message-Passing MAP Inference with Logical Dependencies
S. Bach, B. Huang, L. Getoor. NIPS Workshop on Discrete and Combinatorial Problems in Machine Learning (DISCML) 2014.
Paper

On the Strong Convexity of Variational Inference
B. London, B. Huang, L. Getoor. NIPS Workshop on Advances in Variational Inference 2014.
Paper

Collective Classification of Stance and Disagreement in Online Debate Forums
D. Sridhar, J. Foulds, B. Huang, M. Walker, L. Getoor. Bay Area Machine Learning Symposium 2014.
Paper

Probabilistic Soft Logic for Social Good
S. Bach, B. Huang, L. Getoor. KDD Workshop on Data Science for Social Good 2014.
Paper

Understanding MOOC Discussion Forums using Seeded LDA
A. Ramesh, D. Goldwasser, B. Huang, H. Daumé III, L. Getoor. ACL Workshop on Innovative Use of NLP for Building Educational Applications, 2014.
Paper

Uncovering Hidden Engagement Patterns for Predicting Learner Performance in MOOCs
A. Ramesh, D. Goldwasser, B. Huang, H. Daumé III, L. Getoor. ACM Conference on Learning at Scale, Works-in-Progress Track. 2014.
Paper

2013

A Hypergraph-Partitioned Vertex Programming Approach for Large-Scale Consensus Optimization.
H. Miao, X. Liu, B. Huang, L. Getoor. IEEE International Conference on Big Data, 2013.
Paper

Hinge-Loss Markov Random Fields: Convex Inference for Structured Prediction
S. Bach, B. Huang, B. London, L. Getoor. Conference on Uncertainty in Artificial Intelligence (UAI) 2013.
Paper

Collective Stability in Structured Prediction: Generalization from One Example
B. London, B. Huang, B. Taskar, L. Getoor. International Conference on Machine Learning (ICML) 2013. Oral presentation.
Paper

A Flexible Framework for Probabilistic Models of Social Trust
B. Huang, A. Kimmig, L. Getoor, J. Golbeck. International Conference on Social Computing, Behavioral-Cultural Modeling, and Prediction (SBP) 2013.
Paper

Large-Margin Structured Learning for Link Ranking
S. Bach, B. Huang, L. Getoor. NIPS Workshop on Frontiers of Network Analysis 2013. Best Student Paper Award.
Paper

Modeling Learner Engagement in MOOCs using Probabilistic Soft Logic
A. Ramesh, D. Goldwasser, B. Huang, H. Daumé III, L. Getoor. NIPS Workshop on Data Driven Education 2013.
Paper

PAC-Bayes Generalization Bounds for Randomized Structured Prediction
B. London, B. Huang, B. Taskar, L. Getoor. NIPS Workshop on Perturbation, Optimization, and Statistics 2013.
Paper

Collective Inference and Multi-Relational Learning for Drug-Target Interaction Prediction
S. Fakhraei, B. Huang, L. Getoor. NIPS Workshop on Machine Learning in Computational Biology 2013

Fairness in Assignment Markets with Dual Decomposition
B. Huang. ICML Workshop on Peer Review and Publishing Models 2013.
Paper

Empirical Analysis of Collective Stability
B. Huang, B. London, B. Taskar, L. Getoor. ICML Workshop on Structured Learning 2013
Paper

Collective Activity Detection using Hinge-Loss Markov Random Fields
B. London, S. Khamis, S. Bach, B. Huang, L. Getoor, L. Davis. CVPR Workshop on Structured Prediction 2013
Paper

Learning Latent Groups with Hinge-Loss Markov Random Fields
S. Bach, B. Huang, L. Getoor. ICML Workshop on Interactions between Inference and Learning (Inferning) 2013
Paper

Graph-Based Generalization Bounds for Learning Binary Relations
B. London, B. Huang, and L. Getoor.
arxiv

Multi-Relational Learning Using Weighted Tensor Decomposition with Modular Loss
B. London, T. Rekatsinas, B. Huang, and L. Getoor.
arxiv

2012

Social Group Modeling with Probabilistic Soft Logic
B. Huang, S. Bach, E. Norris, J. Pujara, and L. Getoor. NIPS 2012 Workshop on Social Network and Social Media Analysis: Methods, Models, and Applications.
Paper

Improved Generalization Bounds for Large-Scale Structured Prediction
B. London, B. Huang, and L. Getoor. NIPS 2012 Workshop on Algorithmic and Statistical Approaches for Large Social Networks.
Paper

Multi-Relational Weighted Tensor Decomposition
B. London, T. Rekatsinas, B. Huang, and L. Getoor. NIPS 2012 Workshop on Spectral Learning.
Paper

A Short Introduction to Probabilistic Soft Logic
A. Kimmig,  S. Bach, M. Broecheler, B. Huang, and L. Getoor. NIPS 2012 Workshop on Probabilistic Programming: Foundations and Applications. Oral presentation
Paper

Probabilistic Soft Logic for Trust Analysis in Social Networks
B. Huang, A. Kimmig, L. Getoor, and J. Golbeck. International Workshop on Statistical Relational Artificial Intelligence (StaRAI). UAI 2012 workshop.
slides

Query-Driven Active Surveying for Collective Classification
G. Namata, B. London, L. Getoor, and B. Huang. International Conference on Machine Learning 2012 Workshop: Mining and Learning with Graphs (MLG). Oral presentation
Paper

Semantic Model Vectors for Complex Video Event Recognition
M. Merler, B. Huang, L. Xie, G. Hua, and A. Natsev. IEEE Transactions on Multimedia, Vol. 14, No. 1, February 2012.
Preprint

Machine Learning for the New York City Power Grid
C. Rudin, D. Waltz, R. Anderson, A. Boulanger, A. Salleb-Aouissi, M. Chow, H. Dutta, P. Gross, B. Huang, S. Ierome, D. Isaac, A. Kressner, R. Passonneau, A. Radeva, and L. Wu. IEEE Transactions on Pattern Analysis and Machine Intelligence. February 2012.
Preprint

2011

Learning a Distance Metric from a Network
B. Shaw, B. Huang, and T. Jebara. Neural Information Processing Systems (NIPS) 2011.
poster

Learning a Degree-Augmented Distance Metric from a Network
B. Huang, B. Shaw, and T. Jebara. Beyond Mahalanobis: Supervised Large-Scale Learning of Similarity. NIPS 2011 workshop. Oral presentation
slides

Learning with Degree-Based Subgraph Estimation
B. Huang
Ph.D. Dissertation. Columbia University
Thesis

Network Prediction with Degree Distributional Metric Learning
B. Huang, B. Shaw, and T. Jebara. Interdisciplinary Workshop on Information and Decision in Social Networks (WIDS 2011).
abstract

Fast b-Matching via Sufficient Selection Belief Propagation
B. Huang and T. Jebara. International Conference on Artificial Intelligence and Statistics (AISTATS) 2011.
clarification.

2010

Collaborative Filtering via Rating Concentration
B. Huang and T. Jebara. International Conference on Artificial Intelligence and Statistics (AISTATS) 2010.
poster

2009

Learning with Subgraph Estimation and Degree Priors
B. Huang and T. Jebara. New York Academy of Sciences Machine Learning Symposium, November 2009.
Paper

Exact Graph Structure Estimation with Degree Priors
B. Huang and T. Jebara. International Conference on Machine Learning and Applications (ICMLA) 2009.
Paper

Alive on Back-Feed Culprit Identification via Machine Learning
B. Huang, A. Salleb-Aouissi, and P. Gross. International Conference on Machine Learning and Applications (ICMLA) 2009. Special Session on Machine Learning in Energy Applications.
Paper

Discovering Characterization Rules from Rankings
A. Salleb-Aouissi, B. Huang, and D. Waltz. International Conference on Machine Learning and Applications (ICMLA) 2009.
Paper

Maximum Entropy Density Estimation with Incomplete Presence-Only Data
B. Huang and A. Salleb-Aouissi.
International Conference on Artificial Intelligence and Statistics (AISTATS) 2009.
poster

Approximating the Permanent with Belief Propagation
B. Huang and T. Jebara. Columbia University Technical Report. 2009
code archive

2008

Maximum Likelihood Graph Structure Estimation with Degree Distributions
B. Huang and T. Jebara. Analyzing Graphs: Theory and Applications, NIPS Workshop, December 2008.
Paper

Vers des Machines a Vecteurs de Support "Actionables": Une Approche Fondee sur le Classement. (Toward Actionable Support Vector Machines: A Ranking Based Approach)
A. Salleb-Aouissi, B. Huang, and D. Waltz. Knowledge Extraction and Management (Extraction et Gestion des Connaissances) EGC 2008, Sophia Antipolis, France. Best Paper Award.

2007

Approximating the Permanent with Belief Propagation
B. Huang and T. Jebara. New York Academy of Sciences Machine Learning Symposium 2007.
abstract

Maximum Entropy Density Estimation with Incomplete Data
B. Huang and A. Salleb-Aouissi. New York Academy of Sciences Machine Learning Symposium 2007.
Poster and abstract.

Loopy Belief Propagation for Bipartite Maximum Weight b-Matching
B. Huang and T. Jebara. International Conference on Artificial Intelligence and Statistics (AISTATS) 2007. Oral presentation.
code.

2006

Loopy Belief Propagation for Bipartite Maximum Weight b-Matching
B. Huang and T. Jebara. New York Academy of Sciences Machine Learning Symposium 2006.
Poster and abstract.

Misc.

spouterprod.c. A useful mex utility to compute sparse outer products in matlab, taking advantage in computation time and memory usage when you are interested in computing something like mask.*(U*V'), where mask is a sparse binary matrix.

Some projects on github.

Image of Columbia University watching Barack Obama's Inauguration

Teaching

A photo of a guitar

Hobbies

Music

When I have free time, I try my best to be a musician. Lately, this is mostly manifested by my playing guitar to entertain my pet budgie.

Recently, I created a few recordings experimenting with the electronic instruments built into Apple GarageBand for iPad, which can be streamed from my SoundCloud page.

In my early high school years, I arranged a number of electronic pieces. Later, in high school and college, I explored combining my electronic songs with real voice and instrument recordings (here is a small subset).

Athletics

During graduate school, I earned a brown belt studying with the Columbia University Tae Kwon Do Club.

A photo of Bert walking in Italy

Links