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