Special Session on Knowledge Discovery with Formal Concept Analysis and related formalisms (FCA4KD++)
A Special Session co-located with the 23rd Int. Symposium on Methodologies for Intelligent Systems (ISMIS 2017) - Warsaw, Poland, June 26-29, 2017
Objectives
Formal Concept Analysis (FCA) is a mathematically well-founded theory aimed at data analysis and classification. FCA allows one to build a concept lattice and a system of dependencies (rules, implications) which can be used for many purposes, e.g. knowledge discovery, learning, biclustering, knowledge representation, reasoning, ontology engineering, information retrieval, recommendation, and text processing. Accordingly, there are many links between FCA and Knowledge Discovery, e.g. pattern mining, but also between FCA and other formalisms such as databases (e.g. functional dependencies), rough sets, fuzzy sets...
Recent years have shown an increased activity in FCA, in particular in extending the possibilities of FCA w.r.t. knowledge processing in all dimensions, such as work on pattern structures and relational concept analysis. These extensions allow FCA to deal with more complex than just binary data (e.g. RDF data), for data analysis, knowledge discovery and knowledge engineering. All these works extend the capabilities of FCA and offer new possibilities for discovery and representation activities.
Accordingly, this special session will be interested in issues such as:
- How can FCA support Knowledge Discovery and Knowledge Engineering, e.g. text mining, RDF data classification, knowledge representation, reasoning, information retrieval, recommendation...
- How can FCA be extended in order to help researchers to solve new and complex problems.
- How relations with other formalisms such as databases, rough sets, fuzzy sets, can be exploited for improving each formalism capabilities?
Topics of interest
The topics include, but not limited to:
- Concept lattices and related structures: description logics, pattern structures, relational structures, rough sets, fuzzy sets...
- Knowledge discovery and data mining with FCA: association rules, itemsets and data dependencies, attribute implications, data pre-processing, redundancy and dimensionality reduction, classification and clustering.
- FCA and Knowledge Engineering: ontology engineering, knowledge representation and reasoning.
- Scalable algorithms for concept lattices "in the large": distributed aspects.
- Applications of concept lattices: text mining, classification and mining in web of data, information retrieval, recommendation, visualization and navigation.
Special Session Organizers
Davide Ciucci (University Milano-Bicocca, Italy)
Sergei O. Kuznetsov (Higher Schools of Economics, Moscow, Russia)
Amedeo Napoli (LORIA (CNRS-Inria-Université de Lorraine), Nancy, France)
Important Dates
Paper submission due: | January 22, 2017 |
Notification of review results: | March 14, 2017 |
Camera ready papers due: | April 3, 2017 |
Proceedings
The accepted papers will be published in ISMIS 2017 proceedings in Springer’s LNAI series.
Paper submission
Authors are invited to submit their manuscripts using the Springer LNCS/LNAI style, with a maximum of 10 pages. Detailed instructions are provided on the conference homepage.
Paper should be submitted in PDF format via ISMIS 2017 Online Submission System (please see http://ismis2017.ii.pw.edu.pl/paper_submission.php).