• Corpus ID: 23031100

Une méthode pour caractériser les communautés des réseaux dynamiques à attributs

@article{Orman2014UneMP,
  title={Une m{\'e}thode pour caract{\'e}riser les communaut{\'e}s des r{\'e}seaux dynamiques {\`a} attributs},
  author={G{\"u}nce Keziban Orman and Vincent Labatut and Marc Plantevit and Jean-François Boulicaut},
  journal={ArXiv},
  year={2014},
  volume={abs/1312.4676}
}
De nombreux systemes complexes sont etudies via l'analyse de reseaux dits complexes ayant des proprietes topologiques typiques. Parmi cellesci, les structures de communautes sont particulierement etudiees. De nombreuses methodes permettent de les detecter, y compris dans des reseaux contenant des attributs nodaux, des liens orientes ou evoluant dans le temps. La detection prend la forme d'une partition de l'ensemble des noeuds, qu'il faut ensuite caracteriser relativement au systeme modelise… 
2 Citations
Contribution to the interpretation of evolving communities in complex networks : Application to the study of social interactions. (Contribution à l'interprétation des communautés en évolution dans des réseaux complexes : Application à l'étude des interactions sociales)
TLDR
This thesis proposes a new representation of communities under the form of temporal sequences of topological measures and attribute values associated to individual nodes, and looks for emergent sequential patterns in this dataset, in order to identify the most characteristic community features.
Co-evolution pattern mining in dynamic attributed graphs. (Fouille de motifs de co-evolution dans des graphes dynamiques attribués)
TLDR
This thesis proposes a new pattern domain that has been called co-evolution patterns, and proposes three constraint-based algorithms, called MINTAG, H-MINTAG and Sky-H-MintAG, that are complete to extract the set of all patterns that meet the different constraints.

References

SHOWING 1-10 OF 22 REFERENCES
Constraint-Based Pattern Mining in Dynamic Graphs
  • C. Robardet
  • Computer Science
    2009 Ninth IEEE International Conference on Data Mining
  • 2009
TLDR
This paper proposes to mine dense and isolated subgraphs defined by two user-parameterized constraints to uncover evolving patterns and demonstrates the applicability of the method on several real-world dynamic graphs and extract meaningful evolving communities.
Efficient aggregation for graph summarization
TLDR
This paper introduces two database-style operations to summarize graphs, called SNAP and k-SNAP, that allow users to control the resolutions of summaries and provides the "drill-down" and "roll-up" abilities to navigate through summaries with different resolutions.
Characterizing the Community Structure of Complex Networks
TLDR
A systematic empirical analysis of the statistical properties of communities in large information, communication, technological, biological, and social networks finds that the mesoscopic organization of networks of the same category is remarkably similar.
Mining Cohesive Patterns from Graphs with Feature Vectors
TLDR
This work introduces the novel problem of mining cohesive patterns from graphs with feature vectors, which combines the concepts of dense subgraphs and subspace clusters into a very expressive problem definition.
Detection and Interpretation of Communities in Complex Networks: Practical Methods and Application
TLDR
This article first review community detection algorithms and characterize them in terms of the nature of the communities they detect, then focuses on the methodological tools one can use to analyze the obtained community structure, both in termsof topological features and nodal attributes.
Community characterization of heterogeneous complex systems
TLDR
An analytical statistical method for characterizing the communities detected in heterogeneous complex systems that makes use of the hypergeometric distribution to assess the probability that a given property is over-expressed in the elements of a community with respect to all the element of the investigated set.
Subspace Clustering Meets Dense Subgraph Mining: A Synthesis of Two Paradigms
TLDR
This work proposes a method for finding homogeneous groups by joining the paradigms of subspace clustering and dense sub graph mining, i.e. sets of nodes that show high similarity in subsets of their dimensions and that are as well densely connected within the given graph.
Constraint-Based Mining of Sets of Cliques Sharing Vertex Properties
TLDR
A method to compute all maximal homogeneous clique sets that satisfy user-defined constraints on the number of separated cliques, on the size of the clique, and on theNumber of labels shared by all the vertices is proposed.
Fast unfolding of communities in large networks
TLDR
This work proposes a heuristic method that is shown to outperform all other known community detection methods in terms of computation time and the quality of the communities detected is very good, as measured by the so-called modularity.
Entropy based community detection in augmented social networks
TLDR
This paper proposes a new method which uses the semantic information along with the network structure in the community detection process and combines an algorithm for optimizing modularity and an entropy-based data clustering algorithm, which tries to find a partition with low entropy and keeping in mind the modularity.
...
...