Explanatory Data Analysis group

Information Theoretic Data Mining '21-'22

Part of
MSc Computer Science
Lecturer
Matthijs van Leeuwen
Assistants
Lincen Yang, Ioanna Papagianni
News
  • 21.07.21 Below is the preliminary schedule for the 2021-2022 edition of this course. Attendance of all course meetings is mandatory. Note that this course has a strict limit on the number of students that can participate. Enroll by 1) registering for the course in uSis; and 2) e-mailing the lecturer to confirm your participation. Further information will be provided via Brightspace.
Introduction

How can we gain insight from data? How can we discover and explain structure in data if we don't know what to expect? What is the optimal model for our data? How do we develop principled algorithms for exploratory data mining? To answer these questions, we study and discuss the state of the art in the relatively young research area of information theoretic data mining. We focus on theory, problems, and algorithms, not on implementation and experimentation.

Contents and schedule

The following provides an overview of the contents and schedule of the course; abbreviations for class types are explained below. Slides and literature will be made available on Blackboard.

# Date Type Topic Mandatory Optional
1 Thu 9 Sep L Introduction [2](1.2-1.6) [1](Ch1-6)
2 Thu 16 Sep L Kolmogorov complexity [2](1.7-1.8,2-2.1.1,8.3-8.3.3,8.4) [4] [5,6]
3 Thu 23 Sep L The Minimum Description Length principle [3](Ch1-3,5)
Thu 30 Sep No class (self-study)
4 Thu 7 Oct L Pattern-based modelling [7] [8,19]
5 Thu 14 Oct S Coding for exploratory data analysis [7,9,10] [11-13]
6 Thu 21 Oct S Finding good models [7,10,14] [11,15]
7 Thu 28 Oct L The Maximum Entropy principle [16] [17,18]
Thu 4 Nov No class
Thu 11 Nov No class
8 Thu 18 Nov P Presentations #1
9 Thu 25 Nov P Presentations #2
10 Thu 2 Dec P Presentations #3
11 Thu 9 Dec P Presentations #4
Thu 30 Dec Essay submission deadline
Class types explained
L
Lecture; just sit back, pay attention, and ask questions when needed/useful; you can read the literature afterwards
S
Seminar; your active contribution is expected, prepare by reading the mandatory literature in advance
P
Student presentations; your active contribution is expected, but no need to prepare (unless you present, of course)
Examination

Attendance of all twelve course meetings is mandatory. The final mark is composed of three assignments (15%); presentation (including Q&A) (25%); and a scientific essay (60%).

Literature
  1. Wasserman, L. All of Statistics - A Concise Course in Statistics, Springer, 2004.
  2. Ming, L & Vitányi, PMB. An Introduction to Kolmogorov Complexity and Its Applications (3rd ed), Springer, 2008.
  3. Grünwald, P. The Minimum Description Length Principle, MIT Press, 2007.
  4. Campana, BJL & Keogh, EJ. A Compression-Based Distance Measure for Texture. In: Proceedings of SIAM Data Mining (SDM'10), 2010.
  5. Faloutsos, C & Megalooikonomou, V. On data mining, compression, and Kolmogorov complexity. In: Data Min. Knowl. Discov. 15(1):3-20, 2007.
  6. Cilibrasi, R & Vitányi, PMB. Clustering by Compression. In: IEEE Transactions on Information Theory 15(4):1523-1545, 2005.
  7. Vreeken, J, van Leeuwen, M & Siebes, A. Krimp: Mining Itemsets that Compress. In: Data Min. Knowl. Discov. 23(1):169-214, 2011.
  8. van Leeuwen, M & Vreeken, J. Mining and Using Sets of Patterns through Compression. In CC Aggarwal & J Han, eds, Frequent Pattern Mining, Springer, 2014.
  9. Budhathoki, K & Vreeken, J. The Difference and the Norm – Characterising Similarities and Differences between Databases. In: Proceedings of European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), pp 206-223, 2015.
  10. van Leeuwen, M & Galbrun, E. Association Discovery in Two-View Data. Transactions on Knowledge and Data Engineering 27(12):3190-3202, 2015.
  11. Tatti, N & Vreeken, J. The Long and the Short of It: Summarising Event Sequences with Serial Episodes. In: Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), pp 462-470, 2012.
  12. 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), pp 91-99, 2014.
  13. Tatti, N & Vreeken, J. Finding Good Itemsets by Packing Data. In: Proceedings of the IEEE International Conference on Data Mining (ICDM), pp 588-597, 2008.
  14. Smet, K & Vreeken, J. SLIM: Directly Mining Descriptive Patterns. In: Proceedings of the SIAM International Conference on Data Mining (SDM), pp 236-247, 2012.
  15. Siebes, A & Kersten, R. A Structure Function for Transaction Data. In: Proceedings of the SIAM International Conference on Data Mining (SDM), pp 558-569, 2011.
  16. De Bie, T. An Information Theoretic Framework for Data Mining. In: Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), pp 564-572, 2011.
  17. De Bie, T. Maximum entropy models and subjective interestingness: an application to tiles in binary databases. In: Data Min. Knowl. Discov. 23(3):407-446, 2011.
  18. van Leeuwen, M, De Bie, T, Spyropoulou, E & Mesnage, C. Subjective Interestingness of Subgraph Patterns. In: Machine Learning 105(1):41-75, 2016.
  19. Galbrun, E. The Minimum Description Length Principle for Pattern Mining: A Survey arXiv:2007.14009, 2021.