Jilles Vreeken
Independent Research Group Leader (W2)
Exploratory Data Analysis group
Cluster of Excellence MMCI
Saarland University
Senior Researcher
Databases and Information Systems
Max Planck Institute for Informatics
Campus E 1.7 Room 2.04
66123 Saarbrücken, Germany
jilles@mpi-inf.mpg.de
+49 681 302 71 925
+49 681 302 70 155
Jilles at work in Athens
Jilles at work in Athens

Since October 2013, I lead the independent research group on Exploratory Data Analysis at the DFG cluster-of-excellence on Multimodal Computing and Interaction at the University of Saarland. In addition, I'm affiliated as
Senior Researcher with the Database and Information Systems (D5) group of the Max Planck Institute for Informatics.

My research is mainly concerned with exploratory data mining. That is, I develop theory and algorithms for answering the question `this is my data, tell me what I need to know'. To identify what you need to know, i.e., what is the most interesting structure in the data, I often employ well-founded statistical methods. In particular, Information Theory — the principles of Minimum Description Length (MDL) and Maximum Entropy have proven to be highly valuable tools. Next, I develop highly efficient algorithms for extracting these interesting structures, i.e., models, from very large and complex data—as well as investigate how we can use these structures in a wide range of applications, including identifying rare diseases, e-health, bio-informatics, market analysis, product recommendation, etc.


I'm always looking for talented and motivated PhD candidates, postdocs, and HiWi's
with a strong background in data mining, machine learning, statistics, and/or mathematics.


Currently I'm investigating techniques for identifying informative local structures in large collections of complex data; how to efficiently mine good data descriptions directly such data; the theoretical and practical foundations of interactive exploration of very large data, discovering things by serendipity; how to mine large relational databases; how to mine very large graphs, including characterising influence propagation in social networks; as well as to study well-founded approaches for meaningfully comparing between, and validation of, explorative results.

Below, you'll find an overview of my activities, as well as a selection of my recent publications. You might further be interested in my publications, implementations, our upcoming tutorial on Information Theoretic Methods in Data Mining at ECML PKDD'14, or our workshop on Interactive Data Exploration and Analytics (IDEA) at KDD'14.


or, in case you're looking for a bit of procrastination, consider
Research in Progress — the secret life of research, through the medium of animated GIFs.


Activities more ▾

Teaching more ▾
  • Graduate Courses
  • Undergraduate Courses
    • Artificial Intelligence ('12–'13)
    • Introduction to Artificial Intelligence ('09–'12)
    • Introduction to Data Mining ('09–'11)
    • Internet Programming ('06–'08)
    • Databases ('05–'06)

Selected Recent Publications (go here for the complete list)
In Press
Wu, H, Vreeken, J, Tatti, N & Ramakrishnan, N Uncovering the Plot: Detecting Surprising Coalitions of Entities in Multi-Relational Schemas. Data Mining and Knowledge Discovery, Springer (IF 2.877) (ECML PKDD'14 Journal Track)
Nguyen, H-V, Müller, E, Vreeken, J & Böhm, K Unsupervised Interaction-Preserving Discretization of Multivariate Data. Data Mining and Knowledge Discovery, Springer (IF 2.877) (ECML PKDD'14 Journal Track)implementationwebsite
Miettinen, P & Vreeken, J mdl4bmf: Minimal Description Length for Boolean Matrix Factorization. Transactions on Knowledge Discovery from Data, pp 1-30, ACM (IF 1.68) (In press)implementation
2014
Nguyen, H-V, Müller, E, Vreeken, J & Böhm, K Multivariate Maximal Correlation Analysis. In: Proceedings of the International Conference on Machine Learning (ICML'14), JMLR: W&CP vol.32, 2014. (25.0% acceptance rate)implementationwebsite
Koutra, D, Kang, U, Vreeken, J & Faloutsos, C VoG: Summarizing and Understanding Large Graphs. In: Proceedings of the SIAM International Conference on Data Mining (SDM'14), SIAM, 2014. (fast track journal invitation, as one of the best of SDM'14; full paper with presentation, 15.4% acceptance rate)implementationwebsite
Prakash, BA, Vreeken, J & Faloutsos, C Efficiently Spotting the Starting Points of an Epidemic in a Large Graph. Knowledge and Information Systems vol.38(1), pp 35-59, Springer, 2014. (IF 2.225)implementationwebsite
Webb, G & Vreeken, J Efficient Discovery of the Most Interesting Associations. Transactions on Knowledge Discovery from Data vol.8(3), pp 1-31, ACM, 2014. (IF 1.68)implementation
2013
Akşehirli, E, Goethals, B, Müller, E & Vreeken, J Cartification: A Neighborhood Preserving Transformation for Mining High Dimensional Data. In: Proceedings of the IEEE International Conference on Data Mining (ICDM'13), pp 937-942, IEEE, 2013. (19.6% acceptance rate)website
Ramon, J, Miettinen, P & Vreeken, J Detecting Bicliques in GF[q]. In: Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD'13), pp 509-524, Springer, 2013.implementation
Kontonasios, K-N, Vreeken, J & De Bie, T Maximum Entropy Models for Iteratively Identifying Subjectively Interesting Structure in Real-Valued Data. In: Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD'13), pp 256-271, Springer, 2013.implementation
Nguyen, HV, Müller, E, Vreeken, J, Keller, F & Böhm, K CMI: An Information-Theoretic Contrast Measure for Enhancing Subspace Cluster and Outlier Detection. In: Proceedings of the SIAM International Conference on Data Mining (SDM'13), pp 198-206, SIAM, 2013. (oral presentation, 14.4% acceptance rate; overal 25%)website
Akoglu, L, Vreeken, J, Tong, H, Chau, DH, Tatti, N & Faloutsos, C Mining Connection Pathways for Marked Nodes in Large Graphs. In: Proceedings of the SIAM International Conference on Data Mining (SDM'13), pp 37-45, SIAM, 2013. (oral presentation, 14.4% acceptance rate; overal 25%)implementation
Mampaey, M & Vreeken, J Summarizing Categorical Data by Clustering Attributes. Data Mining and Knowledge Discovery vol.26(1), pp 130-173, Springer, 2013. (IF 2.877)implementation