Machine Learning Research Group

Research

We work on machine learning and applications in the areas of information retrieval and language processing. Currently, our work focuses on the following research topics.

• Transfer learning, learning when training and test distributions differ.
• Adversarial learning.
• Exploratory text analysis and visualization.
• Discriminative, structured prediction.

Current Funded Projects

Prediction Games

Funding: German Science Foundation DFG
Duration: 2010-2013

Most results on machine learning rely on the assumption that training data reflect the future behavior of the system under investigation. This assumption over-simplifies reality when an active adversary can exercise some control on the future behavior of the system. This is the case, for instance, with the identification of phishing attacks or credit card fraud. Here, model building becomes a game between learner and adversary. Game theory models such interactions as interleaved optimization problems. Since data-dependent optimization criteria are not a focus of game theory, many questions remain open today. Based on game-theoretic paradigms that model various patterns of interaction between players, the project aims at analyzing prediction games. In particular, the project will investigate learning models that constitute optimal solution to prediction games under defined circumstances.

Multimedia Retrieval

Funding: STRATO AG
Duration: Since 2009

The goals of this project is to evaluate and develop thechnology that allows to implement intuitive and intelligent ways of navigating large photo and video collections.

Security

Funding: Strato Rechenzentrum AG
Duration: since 7/2005

Strato is a European provider of webspace and server hosting services. We analyze the adversarial classification problem of spam identification. Spam filtering is a game between two opponents, spam sender and spam filter, that react to each other's moves. We seek to identify a winning strategy that cannot easily be dodged by spam senders. In cooperation with Strato AG, we have developed a spam filter that now processes roughly 1 percent of all emails sent and received worldwide.

Intrusions are attempted on a daily basis. Usually, attackers seek to exploit insecure web sites in order to send huge amounts of spam emails via Strato's email servers. We develop an intelligent monitoring system that tracks http requests and discriminates ligitimate use of a web site from attempts to exploit insecure scripts.

Modelling and Optimization of Dialysis Treatment

Funding: Fresenius-affiliate NephroCare e-Services GmbH
Duration: since 04/2008

We investigate model-building and the generation of actionable knowledge from records of dialysis treatments.

Scalable Ranking of Online Ads

Funding: nugg.ad AG
Duration: since 02/2007

In this project, we investigate efficient algorithms that predict which ad a user is most likely to click at, based on that user's past clicking behavior and all other information that is available.

Completed Projects

Differing Training and Test Distributions in Active Learning

Funding: Google Research Award
Duration: 2009

Active learning reduces the labeling effort incurred by applying machine learning algorithms. Active learning procedures direct the attention of a labeler towards examples whose label is believed to convey a maximum of information. Labeled samples in active learning are governed by a distribution that differs from the natural test distribution for multiple reasons. An initial labeled sample may be compiled from auxiliary data sources; the natural input distribution may change over time, or may be altered by an adversary. In addition - and specific to active learning - an active instance selection procedure creates a labeled sample that is biased by the selection criterion. Treating the artificially selected sample in active learning as if it was governed by the test distribution is not necessarily the best course of action. We will understand, develop, and evaluate systematic approaches to active learning that account for this discrepancy between labeled training and test distributions.

Mining Jazz Data to Assess Development Processes

Funding: IBM, Jazz Faculty Grant
Duration: 01/2008-12/2008
Principal Investigators: Andreas Zeller, Tobias Scheffer

What is it that makes a good development process? We want to develop a plug-in that learns from collaboration and defect data as tracked by Jazz, relates features of the collaborative development process to the defect density of individual components, and thereby automatically predicts code quality. For instance, the plug-in might advise that package P should be reviewed more, because a new dependency on compiler internals has been added shortly before the release date by a developer who is new to the team.

Text Mining: Knowledge Discovery in Text Databases and Efficient Document Processing

(German project title: Text Mining: Wissensentdeckung in Textsammlungen und Effizienz von Dokumentenverarbeitungsprozessen)

Funding: German Science Foundation DFG
Duration: June 2003 through June 2008

The amount of documents available in archives and on the web is growing exponentially. This growth induces a demand for methods that automatically analyze large volumes of documents, discover and utilize valuable knowledge contained in them. A substantial part of our working processes consists of processing (i.e., reading, writing, manipulating) documents. Many tools support the administration of text documents, such as file systems, databases, or document management systems. Much greater efforts (and more expenses), however, are imposed by the actual document manipulation processes — such as writing documents. Any support of document manipulation processes requires substantial knowledge; it is therefore much more difficult to support document processing rather than document administration.
The goal of the „Text Mining“ project is to develop and study text mining algorithms that discover knowledge in large document archives, and utilize this knowledge to support future text manipulation processes.

• One of the project goals lies in the development, and in studying the properties of, efficient active learning algorithms that generate sequence models from example documents. Such statistical models are able to segment, classify, and extract information from documents. In several ways, statistical sequence models can be used to support, and enhance the efficiency of, document manipulation processes.
• While text mining methods allow to extract information from textual documents and to translate this information into structured representation, data mining algorithms are able to discover knowledge (e.g., patterns or rules) in structured databases. Our goal is to study how these steps can be interleaved automatically, allowing discovery of knowledge that is hidden in textual archives.
• Our ultimate project goal is to develop and study methods that discover knowledge in document archives, and utilize this knowledge to effectively support future document manipulation processes. Prototypically, we will develop a sentence completion function for natural language. Based on stored documents, the system is to generate a domain and user specific language model representing frequently used phrases and their semantic context. In the application phase, the system will analyze text fragments entered by the user of – for instance – a word processing system. Based on the analysis of text fragment entered so far, the system will propose the most likely completion of a sentence, if this completion can be derived from the acquired knowledge.

Data and Text Mining in Quality and Service

Funding: DaimlerChrysler AG
Duration: 08/2005-07/2008

We study the problem of discovering trends and new developments in production and warranty databases as well as in workshop reports. We develop technologies that automatically identify such trends and discover their hidden causes. The goal of this project is the constructive analysis of data mining methods that lead to improved service processes by integrating and analyzing textual information and data from multiple, heterogeneous and distributed databases.