Morpho-statistical description of networks through graph modelling and Bayesian inference

Quentin Laporte-Chabasse (1, 2) , Marianne Clausel (3) , Radu Stoica (3) , François Charoy (1) , Gérald Oster (1)

1 COAST - Web Scale Trustworthy Collaborative Service Systems
2 LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
3 IECL - Institut Élie Cartan de Lorraine

Collaboration graphs are relevant sources of information to understand behavioural tendencies of groups of individuals. The study of these collaboration graphs enables figuring out factors that may affect the efficiency and the sustainability of cooperative work. An example of such a collaboration involves researchers who develop relationships with their external counterparts to tackle scientific challenges. We propose a statistical approach that considers edge occurrence in the graph as a labelling process. Our approach combines spatial processes modelling and Exponential Random Graph Models (ERGMs) commonly used to analyse such social processes. Since the normalising constant involved in classical Markov Chain Monte Carlo approaches is not available in an analytic closed form, the inference remains challenging. To overcome this issue, we propose a Bayesian tool that relies on the recent ABC Shadow algorithm. The proposed method is illustrated on real data sets from an open archive of scholarly documents.

Domaines: Réseaux sociaux et d'information [cs.SI]; Statistiques [math.ST]

Quentin Laporte-Chabasse, Marianne Clausel, Radu Stoica, François Charoy, Gérald Oster. Morpho-statistical description of networks through graph modelling and Bayesian inference. 2020. ⟨hal-02421787v2⟩