The results of the survey and some of the presentation slides are now available on-line.


Over the last decade, the field of local pattern discovery has grown rapidly, and a range of techniques is available for producing extensive collections of patterns. Because of the exhaustive nature of most such techniques, the pattern collections provide a fairly complete picture of the information content of the database. However, in many cases this is where the process stops. The so-called local patterns represent fragmented knowledge, and often it is not clear how the pieces of the puzzle can be combined into a global model. Because a useful global model, such as a classifier or regression model, is often the expected result of a Data Mining process, the question of how to turn large collections of patterns into global models deserves attention.

In this workshop, we will deal with the question of how to convert local patterns into an actionable global model, for example a classifier or regression model. Global modeling in this setting entails combining patterns effectively and dealing with possible redundancy or conflicts between the reported patterns. In our view, a common ground of all the local pattern mining techniques is that they can be considered to be feature construction techniques that follow different objectives (or constraints).

Workshop Goals

The goal of this workshop is to bring people that work on various aspects of this subject into a fruitful dicussion about the state-of-the-art and the remaining open problems, about commonalities and differences in their respective works. Some research questions, which we consider to be particularly relevant are:

Metrics for Pattern Set Selection:
Evaluation metrics for local and global models have been investigated in quite some depth. However, for the Pattern Set Discovery task, which does not evaluate isolated patterns but pattern sets, it is still quite unclear what types of metrics and constraints can be defined and what effects they will have.
Efficient Pattern Set Discovery:
As an exponential number of subsets exist, exhaustive methods will only work for small pattern collections. How can this process be sped up, and how can good approximations be achieved?
Propagation of Constraints:
How can global constraints be propagated back to local constraints? What type of local patterns must be found in order to guarantee a high performance on the global modeling task? Which local constraints optimize which global constraints?
General-Purpose Constraints:
A key advantage of the modular approach could be that local patterns may be mined independently and can be re-used for several Global Modeling tasks. Are there general local constraints, such as on frequency or entropy, that give a reasonable performance on a wide variety of Global Modeling tasks?


As part of our workshop program, we have put together a questionnaire. You can find the results here.

Please feel free to forward the survey to colleagues that might be interested in the subject, and ask them to send in their opinions as well. Participation in the survey is not restricted to Workshop attendees, and we will continue to update the results if we receive new feedback.

Workshop Format

The workshop will be held as a one-day session with paper presentations. Submitted papers will be reviewed by the programme committee. We will also admit position statements or interesting incomplete or immature work into the program, which will hopefully stimulate discussions, in order to further the main goal of the workshop, namely to increase the awareness of different approaches to this general problem.

Presentation times for the individual papers will be alloted based on the reviews, the length, significance and the expected interest of the contribution (we foresee 10, 20, and 30 minutes presentations). Papers will be arranged into a hopefully coherent program, putting papers that address the same or similar type of problems into the same sessions. Each session is planned to end with a discussion on all presented papers (in addition to the usual question periods after each presentation). Discussions will be stimulated by designated session chairs whose expertise is in the session area.

Topics of Interest

The workshop calls for papers related to global modeling using local patterns. The following is an (incomplete) list of suitable topics. We would like to stress that these topics should be considered in the context of the theme of the workshop. Particularly, papers concerning either global modeling or local pattern discovery in isolation cannot be accepted for inclusion into the workshop program.

  • Associative Classification
  • Combination Strategies
  • Compression-based Pattern Selection
  • Constraint-based Pattern Set Mining
  • Ensembles of Patterns
  • Feature Construction and Selection
  • Global Modeling with Patterns
  • Iterative Local Pattern Discovery
  • KDD Process-models for Building Global Models from Local Patterns}
  • Parallel Universes
  • Pattern Ordering
  • Patterns and Information Theory
  • Pattern Set Selection
  • Pattern Teams
  • Propositionalisation
  • Quality Measures for Pattern Sets
  • Resolution of Conflicting Predictions
  • Subgroup Discovery

Accepted Papers

We accepted the following papers. A schedule for presentations and presentation lengths for individual papers will follow later:
Arno Knobbe, Bruno Crémilleux, Johannes Fürnkranz, Martin Scholz
From Local Patterns to Global Models: The LeGo Approach to Data Mining
Krzysztof Dembczynski, Wojciech Kotlowski, Roman Slowinski
A General Framework for Learning an Ensemble of Decision Rules
Arnaud Giacometti, Eynollah Khanjari Miyaneh, Patrick Marcel, Arnaud Soulet
A Generic Framework for Rule-Based Classification
Henrik Grosskreutz
Cascaded Subgroups Discovery with an Application to Regression
Ruggero G. Pensa, Miro Nanni
A Constraint-Based Approach for Multispace Clustering
Szymon Jaroszewicz
Interactive HMM Construction Based on Interesting Sequences
Hassan H. Malik, John R. Kender
Classification by Pattern-Based Hierarchical Clustering
Hassan H. Malik, John R. Kender
Instance Driven Hierarchical Clustering of Document Collections
Martin Mozina, Ivan Bratko
Rectifying Predictions of Classifiers by Local Rules
Stefan Rüping
Globalization of Local Models with SVMs
Jan-Nikolas Sulzmann, Johannes Fürnkranz
A Comparison of Techniques for Selecting and Combining Class Association Rules
Albrecht Zimmermann, Björn Bringmann
What matters: Size does, Smarts Don't
We will edit on-line proceedings of all accepted papers so that the results are widely accessible. If there is sufficient interest and quality of the papers, we will also consider a post-workshop publication (e.g., as a special issue in a journal).


09:00 - 09:15Welcome and overview
09:15 - 09:30Background Talk:An Introduction to LeGo (A. Knobbe) [Slides]
09:30 - 10:00A General Framework for Learning an Ensemble of Decision Rules (K. Dembczynski, W. Kotlowski and R. Slowinski) [Slides]
10:00 - 10:20Globalization of Local Models with SVMs (S. Rüping)
10:20 - 10:45Coffee break
10:45 - 11:00Background Talk:Pattern Subset Selection (J. Vreeken) [Slides]
11:00 - 11:30A Comparison of Techniques for Selecting and Combining Class Association Rules (J.-N. Sulzmann, J. Fürnkranz)
11:30 - 11.50What matters: Size does, Smarts Don't (A. Zimmermann, B. Bringmann)
11:50 - 12:20Interactive HMM Construction Based on Interesting Sequences (S. Jaroszewicz) [Slides]
12:20 - 13:45Lunch
13:45 - 14:00Background Talk: Rule-Based Classification (J. Fürnkranz) [Slides]
14:00 - 14:30Cascaded Subgroups Discovery with an Application to Regression (H. Grosskreutz)
14:30 - 14:50A Generic Framework for Rule-Based Classification (A. Giacometti, E. Khanjari Miyaneh, P. Marcel, A. Soulet)
14:50 - 15:10Rectifying Predictions of Classifiers by Local Rules (M. Mozina, I. Bratko)
15:10 - 15:30Coffee break
15:30 - 15:45Background Talk: Parallel Universes (B. Wiswedel) [Slides]
15:45 - 16:05A Constraint-Based Approach for Multispace Clustering (R.G. Pensa, M. Nanni)
16:05 - 16:35Classification by Pattern-Based Hierarchical Clustering/Instance Driven Hierarchical Clustering of Document Collections (H.H. Malik, J.R. Kender) [Slides]
16:35 - 17:15LeGo Discussion & Survey results


  • Johannes Fürnkranz (TU Darmstadt)
  • Arno Knobbe (Utrecht University and Kiminkii)

Programme Committee

(may still be expanded)

  • Martin Atzmüller (Universität Würzburg)
  • Michael Berthold (Universität Konstanz)
  • Björn Bringmann (K.U. Leuven)
  • Henrik Boström (Stockholm University)
  • Bruno Crémilleux (Université de Caen)
  • Henrik Grosskreutz (Fraunhofer IAIS, Bonn)
  • Hannes Heikinheimo (Helsinki University of Technology)
  • Frederik Janssen (TU Darmstadt)
  • Arne Koopman (Universiteit Utrecht)
  • Petra Kralj (Jozef Stefan Institute, Ljubljana)
  • Stefan Kramer (TU München)
  • Nada Lavrač (Jozef Stefan Institute, Ljubljana)
  • Matthijs van Leeuwen (Universiteit Utrecht)
  • Taneli Mielikainen (Nokia)
  • Siegfried Nijssen (K.U. Leuven)
  • Martin Scholz (HP Research)
  • Ulrich Rückert (TU München)
  • Stefan Rüping (Fraunhofer IAIS, Bonn)
  • Jilles Vreeken (Universiteit Utrecht)
  • Albrecht Zimmermann (K.U. Leuven)