Author, as appears in the article.: Vallès-Català T, Peixoto TP, Sales-Pardo M, Guimerà R

Department: Enginyeria Química

URV's Author/s: Guimera Manrique, Roger / Sales Pardo, Marta

Keywords: Hashtag Etiqueta «#» @uroweb @residentesaeu @infoAeu

Abstract: A principled approach to understand network structures is to formulate generative models. Given a collection of models, however, an outstanding key task is to determine which one provides a more accurate description of the network at hand, discounting statistical fluctuations. This problem can be approached using two principled criteria that at first may seem equivalent: selecting the most plausible model in terms of its posterior probability; or selecting the model with the highest predictive performance in terms of identifying missing links. Here we show that while these two approaches yield consistent results in most cases, there are also notable instances where they do not, that is, where the most plausible model is not the most predictive. We show that in the latter case the improvement of predictive performance can in fact lead to overfitting both in artificial and empirical settings. Furthermore, we show that, in general, the predictive performance is higher when we average over collections of models that are individually less plausible than when we consider only the single most plausible model.

Thematic Areas: Zootecnia / recursos pesqueiros Statistics and probability Statistical and nonlinear physics Saúde coletiva Química Physics, mathematical Physics, fluids & plasmas Odontología Medicina ii Medicina i Materiais Matemática / probabilidade e estatística Interdisciplinar Geociências General medicine Farmacia Engenharias iv Engenharias iii Engenharias ii Educação física Educação Economia Condensed matter physics Ciências biológicas ii Ciências biológicas i Ciências ambientais Ciências agrárias i Ciência da computação Biotecnología Biodiversidade Astronomia / física

ISSN: 1063651X

Author's mail: roger.guimera@urv.cat marta.sales@urv.cat

Author identifier: 0000-0002-3597-4310 0000-0002-8140-6525

Record's date: 2023-02-18

Journal volume: 97

Papper version: info:eu-repo/semantics/publishedVersion

Link to the original source: https://journals.aps.org/pre/abstract/10.1103/PhysRevE.97.062316

Licence document URL: http://repositori.urv.cat/ca/proteccio-de-dades/

Papper original source: Physical Review e. 97 (6-1): 062316-

APA: Vallès-Català T, Peixoto TP, Sales-Pardo M, Guimerà R (2018). Consistencies and inconsistencies between model selection and link prediction in networks. Physical Review e, 97(6-1), 062316-. DOI: 10.1103/PhysRevE.97.062316

Article's DOI: 10.1103/PhysRevE.97.062316

Entity: Universitat Rovira i Virgili

Journal publication year: 2018

First page: Article number 062316

Publication Type: Journal Publications