%0 Conference Proceedings %T Knowledge Discovery in Graphs Through Vertex Separation %+ Université du Québec à Montréal = University of Québec in Montréal (UQAM) %+ École polytechnique (X) %+ Ecole Nationale de l'Aviation Civile (ENAC) %A Sarfati, Marc %A Queudot, Marc %A Mancel, Catherine %A Meurs, Marie-Jean %< avec comité de lecture %@ 978-3-319-57350-2 %( Canadian Conference on Artificial IntelligenceAI 2017: Advances in Artificial Intelligence %B AI 2017, 30th Canadian Conference on Artificial Intelligence %C Edmonton, Canada %I Springer %3 Lecture Notes in Computer Science %V 10233 %P pp 203-214 %8 2017-05-16 %D 2017 %R 10.1007/978-3-319-57351-9_25 %K Graph partitioning %K Knowledge discovery %K Vertex Separator Problem %Z Computer Science [cs]/Databases [cs.DB]Conference papers %X This paper presents our ongoing work on the Vertex Separator Problem (VSP), and its application to knowledge discovery in graphs representing real data. The classic VSP is modeled as an integer linear program. We propose several variants to adapt this model to graphs with various properties. To evaluate the relevance of our approach on real data, we created two graphs of different size from the IMDb database. The model was applied to the separation of these graphs. The results demonstrate how the model is able to semantically separate graphs into clusters. %G English %2 https://enac.hal.science/hal-01521890/document %2 https://enac.hal.science/hal-01521890/file/vsp-cai2017.pdf %L hal-01521890 %U https://enac.hal.science/hal-01521890 %~ X %~ ENAC %~ X-DEP %~ UNIV-PARIS-SACLAY %~ OPTIM %~ X-SACLAY