@conference {328, title = {Scalable Probabilistic Causal Structure Discovery}, booktitle = {International Joint Conference on Artificial Intelligence (IJCAI)}, year = {2018}, abstract = {

Complex causal networks underlie many real-world problems, from the regulatory interactions between genes to the environmental patterns used to understand climate change. Computational methods seek to infer these casual networks using observational data and domain knowledge. In this paper, we identify three key requirements for inferring the structure of causal networks for scientific discovery: (1) robustness to noise in observed measurements; (2) scalability to handle hundreds of variables; and (3) flexibility to encode domain knowledge and other structural constraints. We first formalize the problem of joint probabilistic causal structure discovery.\ We develop an approach using probabilistic soft logic (PSL) that exploits multiple statistical tests, supports efficient optimization over hundreds of variables, and can easily incorporate structural constraints, including imperfect domain knowledge. We compare our method against multiple well-studied approaches on biological and synthetic datasets, showing improvements of up to 20\% in F1-score over the best performing baseline in realistic settings.

}, url = {https://bitbucket.org/linqs/causpsl/src/master/}, author = {Dhanya Sridhar and Pujara, Jay and Lise Getoor} } @conference {kouki:icdm17, title = {Collective Entity Resolution in Familial Networks}, booktitle = {IEEE International Conference on Data Mining (ICDM)}, year = {2017}, note = {To Appear}, abstract = {

Entity resolution in settings with rich relational structure often introduces complex dependencies between coreferences. Exploiting these dependencies is challenging {\textendash} it requires seamlessly combining statistical, relational, and logical dependencies. One task of particular interest is entity resolution in familial networks. In this setting, multiple partial representations of a family tree are provided, from the perspective of different family members, and the challenge is to reconstruct a family tree from these multiple, noisy, partial views. This reconstruction is crucial for applications such as understanding genetic inheritance, tracking disease contagion, and performing census surveys. Here, we design a model that incorporates statistical signals, such as name similarity, relational information, such as sibling overlap, and logical constraints, such as transitivity and bijective matching, in a collective model. We show how to integrate these features using probabilistic soft logic, a scalable probabilistic programming framework. In experiments on realworld data, our model significantly outperforms state-of-theart classifiers that use relational features but are incapable of collective reasoning. I

}, url = {https://github.com/pkouki/icdm2017}, author = {Kouki, Pigi and Pujara, Jay and Marcum, Christopher and Koehly, Laura and Lise Getoor} } @conference {tomkins:ijcai17, title = {Disambiguating Energy Disaggregation: A Collective Probabilistic Approach}, booktitle = {International Joint Conference on Artifi cial Intelligence}, year = {2017}, author = {Tomkins, Sabina and Pujara, Jay and Lise Getoor} } @conference {kim:www17, title = {Probabilistic Visitor Stitching on Cross-Device Web Logs}, booktitle = {International Conference on World Wide Web (WWW)}, year = {2017}, pages = {1581{\textendash}1589}, author = {Kim, Sungchul and Kini, Nikhil and Pujara, Jay and Koh, Eunyee and Lise Getoor} } @conference {pujara:emnlp17, title = {Sparsity and Noise: Where Knowledge Graph Embeddings Fall Short}, booktitle = {Conference on Empirical Methods in Natural Language Processing (EMNLP)}, year = {2017}, url = {https://github.com/eriq-augustine/meta-kg}, author = {Pujara, Jay and Eriq Augustine and Lise Getoor} } @conference {kouki:recsys17, title = {User Preferences for Hybrid Explanations}, booktitle = {11th ACM Conference on Recommender Systems (RecSys)}, year = {2017}, author = {Kouki, Pigi and Schaffer, James and Pujara, Jay and ODonovan, John and Lise Getoor} } @conference {sridhar:akbc17, title = {Using Noisy Extractions to Discover Causal Knowledge}, booktitle = {NIPS Workshop on Automated Knowledge Base Construction}, year = {2017}, author = {Dhanya Sridhar and Pujara, Jay and Lise Getoor} } @conference {pujara:starai15, title = {Online Inference for Knowledge Graph Construction.}, booktitle = {Workshop on Statistical Relational AI}, year = {2015}, author = {Pujara, Jay and London, Ben and Lise Getoor and Cohen, William} } @conference {grycner:emnlp15, title = {RELLY: Inferring Hypernym Relationships Between Relational Phrases}, booktitle = {Conference on Empirical Methods in Natural Language Processing}, year = {2015}, author = {Grycner, Adam and Weikum, Gerhard and Pujara, Jay and Foulds, James and Lise Getoor} } @article {pujara:aimag15, title = {Using Semantics \& Statistics to Turn Data into Knowledge}, journal = {AI Magazine}, volume = {36}, number = {1}, year = {2015}, pages = {65{\textendash}74}, author = {Pujara, Jay and Miao, Hui and Lise Getoor and Cohen, William} } @conference {pujara:akbc14, title = {Building Dynamic Knowledge Graphs}, booktitle = {NIPS Workshop on Automated Knowledge Base Construction}, year = {2014}, author = {Pujara, Jay and Lise Getoor} } @conference {pujara:wtbudg13, title = {Joint Judgments with a Budget: Strategies for Reducing the Cost of Inference}, booktitle = {ICML Workshop on Machine Learning with Test-Time Budgets}, year = {2013}, author = {Pujara, Jay and Miao, Hui and Lise Getoor} } @conference {pujara:iswc13, title = {Knowledge Graph Identification}, booktitle = {International Semantic Web Conference (ISWC)}, year = {2013}, note = {Winner of Best Student Paper award}, author = {Pujara, Jay and Miao, Hui and Lise Getoor and Cohen, William} } @conference {pujara:slg13, title = {Large-Scale Knowledge Graph Identification using PSL}, booktitle = {ICML Workshop on Structured Learning (SLG)}, year = {2013}, author = {Pujara, Jay and Miao, Hui and Lise Getoor and Cohen, William} } @conference {pujara:sbd13, title = {Large-Scale Knowledge Graph Identification using PSL}, booktitle = {AAAI Fall Symposium on Semantics for Big Data}, year = {2013}, author = {Pujara, Jay and Miao, Hui and Lise Getoor and Cohen, William} } @conference {pujara:akbc13, title = {Ontology-Aware Partitioning for Knowledge Graph Identification}, booktitle = {CIKM Workshop on Automatic Knowledge Base Construction}, year = {2013}, author = {Pujara, Jay and Miao, Hui and Lise Getoor and Cohen, William} } @conference {pujara:icmlws11, title = {Reducing Label Cost by Combining Feature Labels and Crowdsourcing}, booktitle = {ICML Workshop on Combining Learning Strategies to Reduce Label Cost}, year = {2011}, author = {Pujara, Jay and London, Ben and Lise Getoor} } @conference {pujara:ceas11, title = {Using Classifier Cascades for Scalable E-Mail Classification}, booktitle = {Collaboration, Electronic Messaging, Anti-Abuse and Spam Conference}, series = {ACM International Conference Proceedings Series}, year = {2011}, note = {Winner of a Best Paper award}, publisher = {ACM}, organization = {ACM}, author = {Pujara, Jay and Daume III, Hal and Lise Getoor} } @conference {pujara:nips10, title = {Coarse-to-Fine, Cost-Sensitive Classification of E-Mail}, booktitle = {NIPS Workshop on Coarse-to-Fine Processing}, year = {2010}, author = {Pujara, Jay and Lise Getoor} }