Presentation > Call for papers

This year the 19th edition of the EGC conference will take place in Metz from January 21 to 25, 2019 on CentraleSupélec's Metz Campus.

The Knowledge Extraction and Management Conference EGC is an annual event bringing together researchers and practitioners from disciplines in the field of data and knowledge science. These disciplines include machine learning, engineering and knowledge representation, data and knowledge reasoning, data mining and analysis, information systems, databases, the semantic web and open data, etc.

The processing and integration of data and knowledge sources constantly raises new needs and challenges in terms of methods, techniques and tools for acquiring, classifying, integrating, representing, and storing data, but also to index them, to visualize them, to interact with them, to protect them and especially to transform them into useful, relevant and privacy-preserving knowledge.

In addition to the scalability needs of large data collections, there is the need fo processingr heterogeneous, variable quality and sometimes very dynamic data, ranging from online newspaper articles, to connected temperature sensor, from photo or viral video to the geographical position of cars, short messages from a microblog to linked data from a genomics database, etc.

A major challenge is the development of more transparent data analysis and reasoning algorithms that are able to identify data biases, explain the source of their results, and ensure privacy and equity.

The EGC conference is an opportunity to make academic and industrial actors meet and confront theoretical work and practical applications on real data and to communicate quality work, exchange and promote the cross fertilization of ideas, through the presentation of recent research, industrial developments and original applications.

EGC 2019's proceedings, including articles from oral communications as well as those associated with posters, will appear in an issue of the journal RNTI. The authors of the best articles will be invited to submit an extended version of their articles for publication in international post-editions published by Springer.


Four scientific awards will be awarded at the conference:

  • an award for the category "academic article" (1500 euros),
  • an award for the category "article application" (1500 euros),
  • an award for the "demonstration" category (500 euros),
  • a thesis award (500 euros) awarded to a young doctor whose thesis has been supported for less than three years in themes related to knowledge extraction and  management. More information on the EGC association website.

These prizes will be awarded by a jury composed of members of the steering committee. The thesis prize is the subject of a specific announcement.


Topics of interest for the conference include (non-exhaustive list):

Foundations of Knowledge Extraction and Management

  • supervised learning: deep learning, rule learning, statistical learning, probabilistic models, set methods, regression, unbalanced classes, knowledge-based classification
  • unsupervised learning: partitioning and overlay methods, hierarchical, multi-view, multi-strategy, co-clustering, constrained clustering
  • method of discovery of patterns and sets of patterns: sequences, graphs, tensors.
  • theoretical framework for data mining, declarative query languages for data mining, constrained data mining, incremental methods
  • scalable data mining algorithms, distributed / parallel systems for data mining
  • statistical methods in data mining
  • inductive logic programming
  • topological learning, mathematical varieties
  • analysis of symbolic data
  • detection of exceptions, unexpected, anomalies, weak signals.
  • visualization and visual excavation of massive data
  • querying and reasoning on data using ontologies
  • representation, processing and exchange of data and knowledge on the Semantic Web and the Web of related data
  • variety of data and complex data: structured, semi-structured, textual data; temporal, spatial, geolocated data; multimedia data; relational data; network data, in graphs;
  • dynamic data; data flow ; annotated data using ontologies; semantically heterogeneous data
  • privacy
  • transparency, fairness and explicability of data processing and analysis algorithms

Methodological Aspects of Knowledge Extraction and Management

  • acquisition, cleaning, filtering of data, reduction of dimensions, selection and modification of characteristics
  • knowledge and ontology management (acquisition, storage, update, interoperability, interconnection, evolution)
  • life cycle and alignments of vocabularies (ontologies, thesaurus, metadata) on the Web
  • preparation, architecture and related data models on the Web.
  • integration of knowledge in the extraction process (ontologies, expertise, ...)
  • traceability, security and integrity of information and data
  • platforms and systems for extracting and managing data and knowledge
  • experimental studies on large data
  • interaction and active learning
  • visualization, explanation and understanding of results
  • criteria and evaluation of data quality, knowledge extracted
  • evaluation protocols and validation of models from users
  • human-machine interaction in data mining


Knowledge Extraction and Management in emerging or related fields

  • link analysis, online communities, social networks, social media
  • digging of opinions, news, microblogging data
  • mobility, geo-localization, knowledge discovery and ubiquity, ambient intelligence, sensor networks, internet of things
  • Big data and new paradigms of data processing: high performance computing, parallelism, distributed systems
  • crowdsourcing, behavior modeling
  • Web data mining, Semantic Web extraction, Web resource annotation, Web of Objects annotation
  • cross-fertilization between knowledge extraction and other fields of research or applications: artificial intelligence, social sciences and humanities, automatic language processing, image processing, computer vision.

Applications of Knowledge Extraction and Management

  • sustainable development, transport and smart places- green computing for knowledge management and extraction
  • epidemic modeling, clinical research, medicine, biology
  • intrusion detection, fraud prevention, security
  • corporate memories, technology watch, economic intelligence
  • referral system, e-commerce, online advertising
  • applications in other fields such as chemistry, environment, social sciences, education, economics, finance, tourism, defense, software engineering.
Online user: 1