Demonstration venue · read-only. Every page can be browsed; the buttons that would change it are switched off. Create an account to run TaxoReview on your own data. A simulation from public publication records: the people listed were not invited and did not agree to review.
? Tutorial for this page
Demo Data from EDBT 2026 / reviewers in the wild / expert

Sandrine Péché

dblp:239/5600 · DBLP profile ↗
← Back
1ranked-venue papers
1as first author
0since 2021 · last 2020
—ORCID · none

Domains — the database's venue-derived domains; a paper can count in several

Artificial intelligence and machine learning · 1 · 1 first-author

Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.

Artificial intelligence
1 paper
Graph learning · 67% Learning theory · 33%
Theoretical computer science
1 paper
Graph algorithms and graph theory · 50% Information theory · 50%

Topics — the 5 heaviest of 5, each with the papers that count most for it

TopicWeightPapersLastEvidence papers
Machine learning › Graph learning
graph clustering		 0.412020
Robustness of Community Detection to Random Geometric Perturbations · NeurIPS 2020
Machine learning › Learning theory
spectral methods		 0.412020
Robustness of Community Detection to Random Geometric Perturbations · NeurIPS 2020
Machine learning › Graph learning
stochastic block model		 0.412020
Robustness of Community Detection to Random Geometric Perturbations · NeurIPS 2020
Graph algorithms and graph theory › random graphs
random geometric graphs		 0.412020
Robustness of Community Detection to Random Geometric Perturbations · NeurIPS 2020
Information theory › signal processing
spectral estimation		 0.412020
Robustness of Community Detection to Random Geometric Perturbations · NeurIPS 2020

Methods — techniques the papers use, named apart from their topics

spectral methods · 0.9adjacency matrix analysis · 0.9
YearPublicationVenuePosition
2020 Robustness of Community Detection to Random Geometric Perturbations
abstract
We consider the stochastic block model where connection between vertices is perturbed by some latent (and unobserved) random geometric graph. The objective is to prove that spectral methods are robust to this type of noise, even if they are agnostic to the presence (or not) of the random graph. We provide explicit regimes where the second eigenvector of the adjacency matrix is highly correlated to the true community vector (and therefore when weak/exact recovery is possible). This is possible thanks to a detailed analysis of the spectrum of the latent random graph, of its own interest.
Sandrine Péché, Vianney Perchet
 NeurIPS1