Lilyana Mihalkova

Learning statistical models from relational data

Statistical Relational Learning (SRL) is a subarea of machine learning which combines elements from statistical and probabilistic modeling with languages which support structured data representations. In this survey, we will: 1) provide an introduction to SRL, 2) describe some of the distinguishing characteristics of SRL systems, including relational feature construction and collective classification, 3) describe three SRL systems in detail, 4) discuss applications of SRL techniques to important data management problems such as entity resolution, selectivity estimation, and information integration, and 5) discuss connections between SRL methods and existing database research such as probabilistic databases.

Experiments on Ensembles with Missing and Noisy Data

One of the potential advantages of multiple classifier systems is an increased robustness to noise and other imperfections in data. Previous experiments on classification noise have shown that bagging is fairly robust but that boosting is quite sensitive. Decorate is a recently introduced ensemble method that constructs diverse committees using artificial data. It has been shown to generally outperform both boosting and bagging when training data is limited. This paper compares the sensitivity of bagging, boosting, and Decorate to three types of imperfect data: missing features, classification noise, and feature noise. For missing data, Decorate is the most robust. For classification noise, bagging and Decorate are both robust, with bagging being slightly better than Decorate, while boosting is quite sensitive. For feature noise, all of the ensemble methods increase the resilience of the base classifier.

Lifted graphical models: a survey

Lifted graphical models provide a language for expressing dependencies between different types of entities, their attributes, and their diverse relations, as well as techniques for probabilistic reasoning in such multi-relational domains. In this survey, we review a general form for a lifted graphical model, a par-factor graph, and show how a number of existing statistical relational representations map to this formalism. We discuss inference algorithms, including lifted inference algorithms, that efficiently compute the answers to probabilistic queries over such models. We also review work in learning lifted graphical models from data. There is a growing need for statistical relational models (whether they go by that name or another), as we are inundated with data which is a mix of structured and unstructured, with entities and relations extracted in a noisy manner from text, and with the need to reason effectively with this data. We hope that this synthesis of ideas from many different research groups will provide an accessible starting point for new researchers in this expanding field.

Learning to Disambiguate Search Queries from Short Sessions

Web searches tend to be short and ambiguous. It is therefore not surprising that Web query disambiguation is an actively researched topic. To provide a personalized experience for a user, most existing work relies on search engine log data in which the search activities of that particular user , as well as other users, are recorded over long periods of time. Such approaches may raise privacy concerns and may be difficult to implement for pragmatic reasons. We present an approach to Web query disambiguation that bases its predictions only on a short glimpse of user search activity, captured in a brief session of 4---6 previous searches on average. Our method exploits the relations of the current search session to previous similarly short sessions of other users in order to predict the users intentions and is based on Markov logic, a statistical relational learning model that has been successfully applied to challenging language problems in the past. We present empirical results that demonstrate the effectiveness of our proposed approach on data collected from a commercial general-purpose search engine.

Active inference for retrieval in camera networks

We address the problem of searching camera network videos to retrieve frames containing specified individuals. We show the benefit of utilizing a learned probabilistic model that captures dependencies among the cameras. In addition, we develop an active inference framework that can request human input at inference time, directing human attention to the portions of the videos whose correct annotation would provide the biggest performance improvements. Our primary contribution is to show that by mapping video frames in a camera network onto a graphical model, we can apply collective classification and active inference algorithms to significantly increase the performance of the retrieval system, while minimizing the number of human annotations required.

Exploiting statistical and relational information on the web and in social media

The popularity of Web 2.0, characterized by a proliferation of social media sites, and Web 3.0, with more richly semantically annotated objects and relationships, brings to light a variety of important prediction, ranking, and extraction tasks. The input to these tasks is often best seen as a (noisy) multi-relational graph, such as the click graph, defined by user interactions with Web sites; and the social graph, defined by friendships and affiliations on social media sites. This tutorial will provide an overview of statistical relational learning and inference techniques, motivating and illustrating them using web and social media applications. We will start by briefly surveying some of the sources of statistical and relational information on the web and in social media and will then dedicate most of the tutorial time to an introduction to representations and techniques for learning and reasoning with multi-relational information, viewing them through the lens of web and social media domains. We will end with a discussion of current trends and related fields, such as privacy in social networks.

Reports of the AAAI 2010 Conference Workshops

The AAAI-10 Workshop program was held Sunday and Monday, July 11–12, 2010 at the Westin Peachtree Plaza in Atlanta, Georgia. The AAAI-10 workshop program included 13 workshops covering a wide range of topics in artificial intelligence. The titles of the workshops were AI and Fun, Bridging the Gap between Task and Motion Planning, Collaboratively-Built Knowledge Sources and Artificial Intelligence, Goal-Directed Autonomy, Intelligent Security, Interactive Decision Theory and Game Theory, Metacognition for Robust Social Systems, Model Checking and Artificial Intelligence, Neural-Symbolic Learning and Reasoning, Plan, Activity, and Intent Recognition, Statistical Relational AI, Visual Representations and Reasoning, and Abstraction, Reformulation, and Approximation. This article presents short summaries of those events.