Robust Data Mining of Large-Scale Attributed Graphs

• Applicant: Professor Dr. Stephan Günnemann
• Subject Area: Security and Dependability, Operating-, Communication- and Distributed Systems
• Term: from 2015 to 2022
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 267560157

With the rapid growth of social media, sensor technologies, and life science applications, large-scale attributed graphs have become a ubiquitous and highly informative source of information. Going beyond the description of individual objects by their attributes, the relations between different objects are captured by an underlying graph structure.Since companies and organizations gather these complex data in tremendous sizes, there is an urgent need for automatic analysis techniques. The goal of this project is to develop and analyze robust clustering techniques for large-scale attributed graphs. Specifically, we will tackle two open research challenges: First, in real life applications, attributed graphs are often corrupted, prone to outliers, and vulnerable to attacks. Second, attributed graphs are massive in their size. We aim to explore efficient and highly scalable clustering techniques. The obtained research results will act as a foundation for other mining tasks involving attributed graphs, and they contribute to research and development in areas such as spam and fraud detection, advanced data cleansing, and recommender systems.

• DFG Programme: Independent Junior Research Groups