15th Conference on Knowledge Extraction and Management (EGC 2015)
with Industry Track “Big Data Analytics” held exclusively in English
January 27-30, 2015, Luxembourg
Program chair: - Jérôme Darmont, ERIC – Université de Lyon, France
Local chairs: - Benoît Otjacques, Centre Gabriel Lippmann, Luxembourg - Thomas Tamisier, Centre Gabriel Lippmann, Luxembourg
Industry Track chair: - Patrik Hitzelberger, Centre Gabriel Lippmann, Luxembourg
This French-speaking conference is devoted to theories, methods and applications of knowledge management and engineering, machine learning, data mining and knowledge discovery in databases. EGC aims at providing a forum for researchers, students and professionals for presenting research results. It brings together experts from both academia and industry for exchanging ideas and discussing future challenges in knowledge extraction and management.
As each year, the EGC conference is open to recent research work and industrial developments in the domain of knowledge extraction and management (cf. the list below). Thus, EGC helps present and discuss both theoretical and applied results.
Several kinds of communications are possible: research studies (published as long, 12-page papers, short, 6-page papers or posters with 2-page abstracts, depending on maturity), software demos (presented in 6-page papers) and workshops, which will be part of a separate call for contributions. Papers may be submitted either in French or in English (for non-French speakers). A best academic paper and a best applied paper awards will be granted, as well as a PhD award (separate call pending). Accepted research papers and demos will be published in a special issue of the French RNTI journal. Furthermore, selected accepted papers will be invited to submit an extended version for publication in international postproceedings published by Springer Verlag.
Big Data Analytics will be the topic of the Industry Track of EGC 2015, which will bring together participants from industry and academia. It will be wholly held in English.
Contributions to the Industry Track should emphasize real-world deployment experiences of applications and projects related to the EGC topics (see below), with a special focus on Big Data scenarios. Success stories from the deployment of analytical technologies in industry, and concrete lessons learned can be presented. Areas where further research is needed, opportunities for Big Data analytics in industry, success stories from the deployment of tools and applications – every aspect of the practical current and future use of knowledge extraction and management technologies in industry can and should be discussed.
We encourage submissions from industry, but also from academia when there is a clear practical relevance, and especially from academic/industrial collaboration projects. The review process for this track will mainly focus on practical relevance. Submissions can be short (6 pages max.) or long (12 page max.) papers in English only. They must follow the format and guidelines of the main conference, see below and on the conference website.
Foundations of knowledge extraction and management
Tasks - Supervised learning: kernel machines, vector machines, formal neural networks, probabilistic models, rule learning, ensemble methods, regression… - Clustering: conceptual clustering, partitioning methods, neural methods, hierarchical methods, multiview, multistrategy, incremental, or collaborative clustering - Model selection - Pattern mining: itemsets, sequences, trees, graphs… - Outlier and anomaly detection - Recommendation systems - Other paradigms: semi-supervised, active or multistrategy machine learning
Methods - Statistical methods in data mining - Symbolic learning, inductive logic programming - Topological learning, mathematical varieties - Visual data mining - Data mining and constraints - Incremental data mining - Scalable data mining algorithms - Distributed/parallel systems for data mining - Symbolic data analysis
Data - Structured, semi-structured, textual data… - Semantically heterogeneous data / multimedia, spatial, images, video, audio… data / data populating knowledge models, relational data, network data, graph data - Geolocated, temporal, spatial data - Data annotated with ontologies, exploited within the semantic Web - Voluminous, complex, dynamic data… - Open data - Social data
Methodologies for knowledge extraction and management
Knowledge extraction and management in emerging domains
Applications of knowledge extraction and management
Submission format
Submissions must be anonymous and posted only through the conference’s website.
https://easychair.org/conferences/?conf=egc2015
They must be sent in PDF format only and comply with the RNTI LaTeX format that is downloadable at the following URI.
http://www.editions-rnti.fr/files/RNTI-X-Y2.1.zip
Submissions longer than 12 pages or not complying with the RNTI LaTeX format will not be reviewed.
All dates are firm. There will be no extended deadline.
Research papers - Abstracts: October 10, 2014 - Full papers: October 17, 2014 - Authors/PC members interaction: November 12-14, 2014 - Notification to authors: November 22, 2014 - Final versions: December 10, 2014
Software demos - Submission deadline: October 17, 2014 - Notification to authors: November 22, 2014 - Final versions: December 10, 2014
Workshops - Submission deadline: September 5, 2014 - Notification to workshop chairs: September 15, 2014 - Workshop program online: January 6, 2015