Recent Research

         Large-scale Structured Learning for Hierarchical Classification (Gopal & Yang, KDD 2013; Gopal & Yang, ICML 2013 & Supplementary ; Gopal et al., NIPS 2012)

o   Providing organizational views of multi-source Big Data (e.g., Wikipedia, online shops, Coursera)

o   State-of-the-art classifiers for large-scale classification over hundreds of thousands of categories

o   Scalable variational inference for joint optimization of one trillion (4 TB) model parameters 

         Scalable Machine Learning for Time Series Analysis (Topic Detection and Tracking)

o   From scientific literature, news stories, sensor signals, maintenance reports, etc.

o   Modeling multi-source and multi-scale evidence of dynamic chances in temporal sequences On-going NSF project; Gopal, PhD Thesis)

o   A new family of Bayesian von Mices Fischer (vMF) clustering techniques (Gopal & Yang, ICML 2014 & Supplementary)

o   Unsupervised clustering + semi-supervised metric learning + supervised classification (Gopal & Yang, UAI 2014 & Supplimentary).

         Concept Graph Learning for Online Education ( NSF project; Yang et al., WSDM 2015)

o   Mapping online course materials to Wikipedia categories as the Interlingua (universal concepts)

o   Predicting conceptual dependencies among courses based on partially observed prerequisites

o   Planning customized curriculum for individuals based on backgrounds  and goals

         Large-scale Optimization for Online Advertising: Sponsored search is an important means of Internet monetization, and is the driving force of major search engines today. How to place advertisements to maximize the revenue for search engines, as well as to satisfy the needs of both users and advertising industries is a tough problem. Collaborating with Microsoft Research in Asia, we have developed a new (and the first) probabilistic optimization framework based on joint modeling of per-click auctions and campaign-level guaranteed delivery of advertisements. We also developed a hierarchical divide-&-conquer strategy for solving the very large optimization problem with millions of users/queries (demands) and massive campaigns (supplies) in the ever-evolving Internet. (K Salomatin, PhD Thesis)

         Multi-Task Active Learning: Active learning selects the most informative instances to label in the process of iterative retraining of classification or regression models. MTAL extends this idea by leveraging inter-task dependencies in estimating the impact of newly selected instances, instead of selecting instances for each task in isolation. We have developed a family of MTAL methods called Benevolent Active Learning, to explicitly estimate the impact of supervision across tasks and to leverage various dependence structures (hierarchies, networks, latent-factor correlations). We have also pursued Personalized Active Learning, i.e., we want to optimize the learning curve of the system not only by selecting informative instances to label, but also by selecting the most knowledgeable labelers for the selected instances. (A Harpale, PhD Thesis; J Zhang, PhD Thesis)

         Personalized Email Prioritization based on Content and Social Network Analysis: Statistical learning in personalized email prioritization has been relatively sparse due to privacy issues since people are reluctant to share personal messages and importance judgments with the research community. We have developed PEP methods under the assumption that the system can only access personal email of each user during the training and testing of the model for that user. Specifically, our focus is on the analysis of personal email networks for discovering user groups and inducing social importance features for email senders and receivers from the viewpoint of each particular user. Using a classification framework to model the mapping from email messages to the appropriate personal priority levels, the system leverages both standard features of email messages and induced social features of senders and receivers in an enriched vector space. (S Yoo, PhD Thesis, Yang et al., IEEE Intelligent Systems: Special Issue on Social Learning )

         Macro-Level Information Fusion for Events and Entities: Web pages, blogs, social media and other texts contain many mentions of events and entities. Detecting such redundancy and fusing multiple mentions enables high-precision recognition, enriching the extracted information. For instance an event and important entities may be mentioned by many sentences in one or more documents, and a joint (fused) representation can be both more accurate and informative at the right level of granularity. Using a corporate acquisition event as an example, different (and partially redundant) sentences can mention acquirer, price, date, approvals, joint-management, etc.; these multi-aspect information needs to be jointly extracted into a unified structured form for this event type, with uncertainty estimates in the aggregated representation. We are initiating a project in this area (joint effort with Prof. Jaime Carbonell).