Skip to Main content Skip to Navigation
Conference papers

Anomalous Cluster Detection in Large Networks with Diffusion-Percolation Testing

Abstract : We propose a computationally efficient procedure for elevated mean detection on a connected subgraph of a network with node-related scalar observations. Our approach relies on two intuitions: first, a significant concentration of high observations in a connected subgraph implies that the subgraph induced by the nodes associated with the highest observations has a large connected component. Secondly, a greater detection power can be obtained in certain cases by denoising the observations using the network structure. Numerical experiments show that our procedure's detection performance and computational efficiency are both competitive.
Document type :
Conference papers
Complete list of metadata
Contributor : Corentin Larroche Connect in order to contact the contributor
Submitted on : Sunday, October 3, 2021 - 3:50:38 PM
Last modification on : Tuesday, October 19, 2021 - 11:16:31 AM
Long-term archiving on: : Tuesday, January 4, 2022 - 6:12:15 PM


Publisher files allowed on an open archive


  • HAL Id : hal-03363228, version 1



Corentin Larroche, Johan Mazel, Stephan Clémençon. Anomalous Cluster Detection in Large Networks with Diffusion-Percolation Testing. European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN), Oct 2021, Online, Belgium. ⟨hal-03363228⟩



Record views


Files downloads