@conference {tomkins:lld2017, title = {Detecting Cyber-bullying from Sparse Data and Inconsistent Labels}, booktitle = {Learning with Limited Labeled Data (LLD) NIPS Workshop}, year = {2017}, author = {Tomkins, Sabina and Lise Getoor and Chen, Yunfei and Zhang, Yi} } @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} } @book {fakhraei:book15, title = {Data Analytics for Pharmaceutical Discoveries}, series = {Healthcare Data Analytics}, volume = {1}, year = {2015}, pages = {1--25}, publisher = {CRC Press}, organization = {CRC Press}, edition = {1}, chapter = {1}, author = {Shobeir Fakhraei and Eberechukwu Onukwugha and Lise Getoor} } @conference {fakhraei:biokdd13, title = {Drug-Target Interaction Prediction for Drug Repurposing with Probabilistic Similarity Logic}, booktitle = {KDD Workshop on BIOKDD}, year = {2013}, publisher = {ACM}, organization = {ACM}, abstract = {

The high development cost and low success rate of drug discovery from new compounds highlight the need for methods to discover alternate therapeutic effects for currently approved drugs. Computational methods can be effective in focusing efforts for such drug repurposing. In this paper, we propose a novel drug-target interaction prediction framework based on probabilistic similarity logic (PSL) [5]. Interaction prediction corresponds to link prediction in a bipartite network of drug-target interactions extended with a set of similarities between drugs and between targets. Using probabilistic first-order logic rules in PSL, we show how rules describing link predictions based on triads and tetrads can effectively make use of a variety of similarity measures. We learn weights for the rules based on training data, and report relative importance of each similarity for interaction prediction. We show that the learned rule weights significantly improve prediction precision. We evaluate our results on a dataset of drug-target interactions obtained from Drugbank [27] augmented with five drug-based and three target-based similarities. We integrate domain knowledge in drug-target interaction prediction and match the performance of the state-of-the-art drug-target interaction prediction systems [22] with our model using simple triad-based rules. Furthermore, we apply techniques that make link prediction in PSL more efficient for drug-target interaction prediction.

}, author = {Shobeir Fakhraei and Louiqa Raschid and Lise Getoor} } @conference {moustafa:gdm11, title = {Declarative Analysis of Noisy Information Networks}, booktitle = {ICDE Workshop on GDM}, year = {2011}, abstract = {

There is a growing interest in methods for analyzing data describing networks of all types, including information, biological, physical, and social networks. Typically the data describing these networks is observational, and thus noisy and incomplete; it is often at the wrong level of fidelity and abstraction for meaningful data analysis. This has resulted in a growing body of work on extracting, cleaning, and annotating network data. Unfortunately, much of this work is ad hoc and domain-specific. In this paper, we present the architecture of a data management system that enables efficient, declarative analysis of large-scale information networks. We identify a set of primitives to support the extraction and inference of a network from observational data, and describe a framework that enables a network analyst to easily implement and combine new extraction and analysis techniques, and efficiently apply them to large observation networks. The key insight behind our approach is to decouple, to the extent possible, (a) the operations that require traversing the graph structure (typically the computationally expensive step), from (b) the operations that do the modification and update of the extracted network. We present an analysis language based on Datalog, and show how to use it to cleanly achieve such decoupling. We briefly describe our prototype system that supports these abstractions. We include a preliminary performance evaluation of the system and show that our approach scales well and can efficiently handle a wide spectrum of data cleaning operations on network data.

}, author = {Moustafa, Walaa and Namata, Galileo and Deshpande, Amol and Lise Getoor} } @conference {sharara:icwsm11, title = {Differential Adaptive Diffusion: Understanding Diversity and Learning whom to Trust in Viral Marketing}, booktitle = {ICWSM}, year = {2011}, abstract = {

Viral marketing mechanisms use the existing social network between customers to spread information about products and encourage product adoption. Existing viral marketing modelsfocus on the dynamics of the diffusion process, however theytypically: (a) only consider a single product campaign and (b)fail to model the evolution of the social network, as the trustbetween individuals changes over time, during the course ofmultiple campaigns. In this work, we propose an adaptive viralmarketing model which captures: (1) multiple differentproduct campaigns, (2) the diversity in customer preferencesamong different product categories, and (3) changing confidencein peers{\textquoteright} recommendations over time. By applyingour model to a real-world network extracted from the Diggsocial news website, we provide insights into the effects ofnetwork dynamics on the different products{\textquoteright} adoption. Ourexperiments show that our proposed model outperforms earliernon-adaptive diffusion models in predicting future productadoptions. We also show how this model can be used toexplore new viral marketing strategies that are more successfulthan classic strategies which ignore the dynamic nature ofsocial networks.

}, author = {Sharara, Hossam and Rand, William and Lise Getoor} } @article {chen:pami11, title = {Dynamic Processing Allocation in Video}, journal = {PAMI}, volume = {33}, number = {11}, year = {2011}, pages = {2174-2187}, abstract = {

Large stores of digital video pose severe computational challenges to existing video analysis algorithms. In applying these algorithms, users must often trade off processing speed for accuracy, as many sophisticated and effective algorithms require large computational resources that make it impractical to apply them throughout long videos. One can save considerable effort by applying these expensive algorithms sparingly, directing their application using the results of more limited processing. We show how to do this for retrospective video analysis by modeling a video using a chain graphical model and performing inference both to analyze the video and to direct processing. We apply our method to problems in background subtraction and face detection, and show in experiments that this leads to significant improvements over baseline algorithms.

}, author = {Chen Daozheng and Bilgic Mustafa and Lise Getoor and Jacobs David} } @conference {bach:pmpm10, title = {Decision-Driven Models with Probabilistic Soft Logic}, booktitle = {NIPS Workshop on Predictive Models in Personalized Medicine}, year = {2010}, author = {Bach, Stephen H. and Broecheler, Matthias and Kok, Stanley and Lise Getoor} } @conference {barash:wsm09, title = {Distinguishing Knowledge vs Social Capital in Social Media with Roles and Context}, booktitle = {International Conference on Weblogs and Social Media}, year = {2009}, month = {May}, author = {Barash, Vladimir and Smith, Marc and Lise Getoor and Welser, Howard} } @conference {sharara:asonam09, title = {The Dynamics of Actor Loyalty to Groups in Affiliation Networks}, booktitle = {International Conference on Advances in Social Networks Analysis and Mining}, year = {2009}, month = {July}, author = {Sharara, Hossam and Singh, Lisa and Lise Getoor and Mann, Janet} } @conference {namata:cikm07, title = {A Dual-View Approach to Interactive Network Visualization}, booktitle = {ACM Conference on Information and Knowledge Management}, year = {2007}, author = {Namata, Galileo Mark and Staats, Brian and Lise Getoor and Shneiderman, Ben} } @conference {bilgic:vast06, title = {D-Dupe: An Interactive Tool for Entity Resolution in Social Networks}, booktitle = {Visual Analytics Science and Technology (VAST)}, year = {2006}, month = {October}, address = {Baltimore}, author = {Bilgic, Mustafa and Licamele, Louis and Lise Getoor and Shneiderman, Ben} } @conference {bilgic:gd05, title = {D-Dupe: An Interactive Tool for Entity Resolution in Social Networks}, booktitle = {International Symposium on Graph Drawing}, series = {Lecture Notes in Computer Science}, volume = {3843}, year = {2005}, month = {September}, pages = {505{\textendash}507}, publisher = {Springer}, organization = {Springer}, author = {Bilgic, Mustafa and Licamele, Louis and Lise Getoor and Shneiderman, Ben}, editor = {Patrick Healy and Nikola S. Nikolov} } @conference {bhattacharya:kdd04-wkshp, title = {Deduplication and Group Detection using Links}, booktitle = {ACM SIGKDD Workshop on Link Analysis and Group Detection (LinkKDD)}, year = {2004}, author = {Bhattacharya, Indrajit and Lise Getoor} }