Interferometric Graph Transform for Community Labeling - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Preprints, Working Papers, ... Year : 2021

Interferometric Graph Transform for Community Labeling

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.
Fichier principal
Vignette du fichier
hal_version.pdf (578.22 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03247781 , version 1 (04-06-2021)

Identifiers

Cite

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

Altmetric

Share

Gmail Facebook X LinkedIn More