@article {bac:jmlr17, title = {Hinge-Loss Markov Random Fields and Probabilistic Soft Logic}, journal = {Journal of Machine Learning Research (JMLR)}, volume = {18}, year = {2017}, pages = {1-67}, abstract = {

A fundamental challenge in developing high-impact machine learning technologies is balancing the need to model rich, structured domains with the ability to scale to big data. Many important problem areas are both richly structured and large scale, from social and biological networks, to knowledge graphs and the Web, to images, video, and natural language. In this paper, we introduce two new formalisms for modeling structured data, and show that they can both capture rich structure and scale to big data. The first, hingeloss Markov random fields (HL-MRFs), is a new kind of probabilistic graphical model that generalizes different approaches to convex inference. We unite three approaches from the randomized algorithms, probabilistic graphical models, and fuzzy logic communities, showing that all three lead to the same inference objective. We then define HL-MRFs by generalizing this unified objective. The second new formalism, probabilistic soft logic (PSL), is a probabilistic programming language that makes HL-MRFs easy to define using a syntax based on first-order logic. We introduce an algorithm for inferring most-probable variable assignments (MAP inference) that is much more scalable than general-purpose convex optimization methods, because it uses message passing to take advantage of sparse dependency structures. We then show how to learn the parameters of HL-MRFs. The learned HL-MRFs are as accurate as analogous discrete models, but much more scalable. Together, these algorithms enable HL-MRFs and PSL to model rich, structured data at scales not previously possible.

}, url = {https://github.com/stephenbach/bach-jmlr17-code}, author = {Bach, Stephen H. and Broecheler, Matthias and Huang, Bert and Lise Getoor} } @article {bach:arxiv15, title = {Hinge-Loss Markov Random Fields and Probabilistic Soft Logic}, journal = {ArXiv:1505.04406 [cs.LG]}, year = {2015}, note = {To reference this work, please cite the JMLR paper.}, author = {Bach, Stephen H. and Broecheler, Matthias and Huang, Bert and Lise Getoor} } @conference {sridhar:acl15, title = {Joint Models of Disagreement and Stance in Online Debate}, booktitle = {Annual Meeting of the Association for Computational Linguistics (ACL)}, year = {2015}, author = {Dhanya Sridhar and Foulds, James and Walker, Marilyn and Huang, Bert and Lise Getoor} } @conference {bach:icml15, title = {Paired-Dual Learning for Fast Training of Latent Variable Hinge-Loss MRFs}, booktitle = {International Conference on Machine Learning (ICML)}, year = {2015}, note = {Stephen Bach and Bert Huang contributed equally.}, abstract = {

Latent variables allow probabilistic graphical models to capture nuance and structure in important domains such as network science, natural language processing, and computer vision. Naive approaches to learning such complex models can be prohibitively expensive{\textemdash}because they require repeated inferences to update beliefs about latent variables{\textemdash}so lifting this restriction for useful classes of models is an important problem. Hinge-loss Markov random fields (HL-MRFs) are graphical models that allow highly scalable inference and learning in structured domains, in part by representing structured problems with continuous variables. However, this representation leads to challenges when learning with latent variables. We introduce paired-dual learning, a framework that greatly speeds up training by using tractable entropy surrogates and avoiding repeated inferences. Paired-dual learning optimizes an objective with a pair of dual inference problems. This allows fast, joint optimization of parameters and dual variables. We evaluate on social-group detection, trust prediction in social networks, and image reconstruction, finding that paired-dual learning trains models as accurate as those trained by traditional methods in much less time, often before traditional methods make even a single parameter update.

}, author = {Bach, Stephen H. and Huang, Bert and Boyd-Graber, Jordan and Lise Getoor} } @article {london:stability15, title = {Stability and Generalization in Structured Prediction}, journal = {{\textendash}}, year = {2015}, note = {preprint}, keywords = {PAC-Bayes, generalization bounds, learning theory, structured prediction}, author = {London, Ben and Huang, Bert and Lise Getoor} } @conference {bach:aistats15, title = {Unifying Local Consistency and MAX SAT Relaxations for Scalable Inference with Rounding Guarantees}, booktitle = {Artificial Intelligence and Statistics (AISTATS)}, year = {2015}, author = {Bach, Stephen H. and Huang, Bert and Lise Getoor} } @conference {ramakrishnan:kdd14, title = {{\textquoteleft}Beating the news{\textquoteright} with EMBERS: Forecasting Civil Unrest using Open Source Indicators}, booktitle = {ACM SIGKDD Conference on Knowledge Discovery and Data Mining}, year = {2014}, abstract = {

We describe the design, implementation, and evaluation of EMBERS, an automated, 24x7 continuous system for forecasting civil unrest across 10 countries of Latin America using open source indicators such as tweets, news sources, blogs, economic indicators, and other data sources. Unlike retrospective studies, EMBERS has been making forecasts into the future since Nov 2012 which have been (and continue to be) evaluated by an independent T\&E team (MITRE). Of note, EMBERS has successfully forecast the uptick and downtick of incidents during the June 2013 protests in Brazil. We outline the system architecture of EMBERS, individual models that leverage specific data sources, and a fusion and suppression engine that supports trading off specific evaluation criteria. EMBERS also provides an audit trail interface that enables the investigation of why specific predictions were made along with the data utilized for forecasting. Through numerous evaluations, we demonstrate the superiority of EMBERS over baserate methods and its capability to forecast significant societal happenings.\ 

}, author = {Ramakrishnan, Naren and Butler, Patrick and Self, Nathan and Khandpur, Rupinder and Saraf, Parang and Wang, Wei and Cadena, Jose and Vullikanti, Anil and Korkmaz, Gizem and Kuhlman, Christopher and Marathe, Achla and Zhao, Liang and Ting, Hua and Huang, Bert and Srinivasan, Aravind and Trinh, Khoa and Lise Getoor and Katz, Graham and Doyle, Andy and Ackermann, Chris and Zavorin, Ilya and Ford, Jim and Summers, Kristin and Fayed, Youssef and Arredondo, Jaime and Gupta, Dipak and Mares, David} } @conference {sridhar:baylearn14, title = {Collective classification of stance and disagreement in online debate forums}, booktitle = {Bay Area Machine Learning Symposium (BayLearn)}, year = {2014}, author = {Dhanya Sridhar and Foulds, James and Huang, Bert and Walker, Marilyn and Lise Getoor} } @conference {ramesh:aaai14, title = {Learning Latent Engagement Patterns of Students in Online Courses}, booktitle = {Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence}, year = {2014}, publisher = {AAAI Press}, organization = {AAAI Press}, keywords = {MOOC, learner engagement, probabilistic modeling, structured prediction}, author = {Ramesh, Arti and Goldwasser, Dan and Huang, Bert and Daume III, Hal and Lise Getoor} } @article {fakhraei:tcbb14, title = {Network-Based Drug-Target Interaction Prediction with Probabilistic Soft Logic}, journal = {IEEE/ACM Transactions on Computational Biology and Bioinformatics}, year = {2014}, note = {Code and data: https://github.com/shobeir/fakhraei_tcbb2014}, author = {Fakhraei, Shobeir and Huang, Bert and Raschid, Louiqa and Lise Getoor} } @conference {london:aistats14, title = {PAC-Bayesian Collective Stability}, booktitle = {Proceedings of the 17th International Conference on Artificial Intelligence and Statistics}, year = {2014}, author = {London, Ben and Huang, Bert and Benjamin Taskar and Lise Getoor} } @conference {bach:dssg14, title = {Probabilistic Soft Logic for Social Good}, booktitle = {KDD Workshop on Data Science for Social Good}, year = {2014}, author = {Bach, Stephen H. and Huang, Bert and Lise Getoor} } @conference {bach:discml14, title = {Rounding Guarantees for Message-Passing MAP Inference with Logical Dependencies}, booktitle = {NIPS Workshop on Discrete and Combinatorial Problems in Machine Learning (DISCML)}, year = {2014}, author = {Bach, Stephen H. and Huang, Bert and Lise Getoor} } @conference {london:nips14ws, title = {On the Strong Convexity of Variational Inference}, booktitle = {NIPS Workshop on Advances in Variational Inference}, year = {2014}, author = {London, Ben and Huang, Bert and Lise Getoor} } @conference {ramesh:las13, title = {Uncovering Hidden Engagement Patterns for Predicting Learner Performance in MOOCs}, booktitle = {ACM Conference on Learning at Scale}, series = {Annual Conference Series}, year = {2014}, publisher = {ACM}, organization = {ACM}, keywords = {MOOC, learner engagement, learning analytics, online education, probabilistic modeling, structured prediction}, author = {Ramesh, Arti and Goldwasser, Dan and Huang, Bert and Daume III, Hal and Lise Getoor} } @unpublished {london:arxiv13a, title = {Graph-based Generalization Bounds for Learning Binary Relations}, year = {2013}, note = {http://arxiv.org/abs/1302.5348}, publisher = {University of Maryland College Park}, author = {London, Ben and Huang, Bert and Lise Getoor} } @conference {bach:uai13, title = {Hinge-loss Markov Random Fields: Convex Inference for Structured Prediction}, booktitle = {Uncertainty in Artificial Intelligence}, year = {2013}, abstract = {

Graphical models for structured domains are powerful tools, but the computational complexities of combinatorial prediction spaces can force restrictions on models, or require approximate inference in order to be tractable. Instead of working in a combinatorial space, we use hinge-loss Markov random fields (HL-MRFs), an expressive class of graphical models with log-concave density functions over continuous variables, which can represent confidences in discrete predictions. This paper demonstrates that HLMRFs are general tools for fast and accurate structured prediction. We introduce the first inference algorithm that is both scalable and applicable to the full class of HL-MRFs, and show how to train HL-MRFs with several learning algorithms. Our experiments show that HL-MRFs match or surpass the predictive performance of state-of-the-art methods, including discrete models, in four application domains.

}, author = {Bach, Stephen H. and Huang, Bert and London, Ben and Lise Getoor} } @conference {miao:bigdata13, title = {A Hypergraph-Partitioned Vertex Programming Approach for Large-scale Consensus Optimization}, booktitle = {2013 IEEE International Conference on Big Data}, year = {2013}, author = {Miao, Hui and Liu, Xiangyang and Huang, Bert and Lise Getoor} } @conference {bach:fna13, title = {Large-margin Structured Learning for Link Ranking}, booktitle = {NIPS Workshop on Frontiers of Network Analysis: Methods, Models, and Applications}, year = {2013}, note = {Winner of Best Student Paper award}, author = {Bach, Stephen H. and Huang, Bert and Lise Getoor} } @conference {bach:inferning13, title = {Learning Latent Groups with Hinge-loss Markov Random Fields}, booktitle = {ICML Workshop on Inferning: Interactions between Inference and Learning}, year = {2013}, author = {Bach, Stephen H. and Huang, Bert and Lise Getoor} } @conference {ramesh:nipsws13, title = {Modeling Learner Engagement in MOOCs using Probabilistic Soft Logic}, booktitle = {NIPS Workshop on Data Driven Education}, year = {2013}, author = {Ramesh, Arti and Goldwasser, Dan and Huang, Bert and Daume III, Hal and Lise Getoor} } @unpublished {london:arxiv13b, title = {Multi-relational Learning Using Weighted Tensor Decomposition with Modular Loss}, year = {2013}, note = {http://arxiv.org/abs/1303.1733}, publisher = {University of Maryland College Park}, author = {London, Ben and Rekatsinas, Theodoros and Huang, Bert and Lise Getoor} } @conference {london:nips13ws, title = {PAC-Bayes Generalization Bounds for Randomized Structured Prediction}, booktitle = {NIP Workshop on Perturbation, Optimization and Statistics}, year = {2013}, author = {London, Ben and Huang, Bert and Benjamin Taskar and Lise Getoor} } @conference {london:nips12asalsn, title = {Improved Generalization Bounds for Large-scale Structured Prediction}, booktitle = {NIPS Workshop on Algorithmic and Statistical Approaches for Large Social Networks}, year = {2012}, author = {London, Ben and Huang, Bert and Lise Getoor} }