Skip to Main content Skip to Navigation
New interface
Preprints, Working Papers, ...

Interferometric Graph Transform for Community Labeling

Nathan Grinsztajn 1 Louis Leconte 2, 3 Philippe Preux 1 Edouard Oyallon 2 
1 Scool - Scool
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189
Abstract : We present a new approach for learning unsupervised node representations in community graphs. We significantly extend the Interferometric Graph Transform (IGT) to community labeling: this non-linear operator iteratively extracts features that take advantage of the graph topology through demodulation operations. An unsupervised feature extraction step cascades modulus non-linearity with linear operators that aim at building relevant invariants for community labeling. Via a simplified model, we show that the IGT concentrates around the E-IGT: those two representations are related through some ergodicity properties. Experiments on community labeling tasks show that this unsupervised representation achieves performances at the level of the state of the art on the standard and challenging datasets Cora, Citeseer, Pubmed and WikiCS.
Document type :
Preprints, Working Papers, ...
Complete list of metadata
Contributor : Edouard Oyallon Connect in order to contact the contributor
Submitted on : Friday, June 4, 2021 - 12:40:37 PM
Last modification on : Tuesday, December 6, 2022 - 12:42:14 PM
Long-term archiving on: : Sunday, September 5, 2021 - 6:10:44 PM


Files produced by the author(s)


  • HAL Id : hal-03247781, version 1
  • ARXIV : 2106.05875


Nathan Grinsztajn, Louis Leconte, Philippe Preux, Edouard Oyallon. Interferometric Graph Transform for Community Labeling. 2021. ⟨hal-03247781⟩



Record views


Files downloads