Research in Data Mining and Machine Learning has progressed significantly in the last decades, through the development of advanced algorithms and techniques. In the past few years there has been a growing attention to the development of languages for use in data mining and machine learning. Such languages provide common buildings blocks and abstractions, and can provide an alternative interface to advanced algorithms and systems that can greatly increase the utility of such systems.
The workshop aims to bring together researchers and stimulate discussions on languages for data mining and machine learning. Its main motivation is the believe that designing generic and declarative modeling languages for data mining and machine learning, together with efficient solving techniques, is an attractive direction that can boost scientific progress.
Workshop venue: Monday 23 Sept, room R6 at ECMLPKDD in Prague.
Informal online proceedings available as a single PDF file.
09:00--09:15 | LML'13 Introduction by the organizers |
09:15--10:15 | Invited talk: Mobility mining query language
Website
Dino Pedreschi |
10:15--10:30 | A query language for constraint-based clustering
Paper
Website
Antoine Adam and Hendrik Blockeel |
10:30--11:00 | Coffee Break |
11:00--11:30 | Declarative In-Network Sensor Data Analysis
Paper
George Valkanas, Ixent Galpin, Alasdair J.G. Gray, Alvaro A. A. Fernandes, Norman W. Paton and Dimitrios Gunopulos |
11:30--12:00 | Mining (Soft-) Skypatterns using Constraint Programming
Paper
Willy Ugarte Rojas, Patrice Boizumault, Samir Loudni, Bruno Cremilleux and Alban Lepailleur |
12:00--12:30 | Query Rewriting for Rule Mining in Databases
Paper
Website
Brice Chardin, Emmanuel Coquery, Marie Pailloux and Jean-Marc Petit |
12:30--14:00 | Lunch Break |
14:00--14:30 | A Constraint Programming Approach for Mining Sequential Patterns
in a Sequence Database
Paper
Jean-Philippe Métivier, Samir Loudni and Thierry Charnois |
14:30--15:00 | The representation of sequential patterns and their projections
within Formal Concept Analysis,
Paper
Aleksey Buzmakov, Elias Egho, Nicolas Jay, Sergei O. Kuznetsov, Amedeo Napoli and Chedy Raïssi |
15:00--15:15 | Language of Conclusions and Formal Frame for Data Mining
with Association Rules
Paper
Website
Jan Rauch |
15:15--15:30 | Lower and upper queries for graph-mining
Website
Amina Kemmar, Yahia Lebbah, Samir Loudni and Mohammed Ouali |
15:30--16:00 | Coffee Break |
16:00--16:30 | API design for machine learning software: experiences from
the scikit-learn project
Paper
Website
Lars Buitinck, Gilles Louppe, Mathieu Blondel, Fabian Pedregosa, Andreas Müller, Olivier Grisel, Vlad Niculae, Peter Prettenhofer, Alexandre Gramfort, Jaques Grobler, Robert Layton, Jake Vanderplas, Arnaud Joly, Brian Holt and Gaël Varoquaux |
16:30--16:45 | ParaMiner: A generic pattern mining algorithm for multi-core architectures
Paper
Website
Benjamin Negrevergne, Alexandre Termier, Marie-Christine Rousset and Jean-François Méhaut |
16:45--17:00 | A declarative query language for statistical inference (extended abstract)
Paper
Gitte Vanwinckelen and Hendrik Blockeel |
17:00--17:30 | Discussion session |
Languages in this workshop can range form query languages and modeling languages to domain specific languages and integration with existing programming languages. Examples include Alchemy, Chrism and ProbLog (probabilistic modeling and inference); Factorie (probabilistic modeling and factor graphs); Dyna (declarative weighted deduction); Learning-based Java (learning based programming); MSQL, Mine Rule, SIQL, SPQL, DMX (data mining query languages); and more.
The workshop promotes work that goes beyond one particular subfield of machine learning or data mining. It promotes cross-fertilisation between computer language oriented research, across data mining and machine learning. The workshop encourages submissions inspired from other scientific disciplines such as logic in knowledge representation, query languages in databases, modeling languages in constraint solving and other formalisms such as mathematical programming.
Our main goal is to stimulate discussion, collaboration and the sharing of experiences. In that respect, we have three submission types:
The following is a non-exclusive list of topics that fit the scope: