Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification

Maximilian Stadler; Bertrand Charpentier; Simon Geisler; Daniel Zügner; Stephan Günnemann

Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification

Maximilian Stadler, Bertrand Charpentier, Simon Geisler, Daniel Zügner, Stephan Günnemann

Informatics 26 - Chair of Professorship of Data Analytics and Machine Learning

Technical University of Munich

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

50 Scopus citations

Abstract

The interdependence between nodes in graphs is key to improve class predictions on nodes and utilized in approaches like Label Propagation (LP) or in Graph Neural Networks (GNNs). Nonetheless, uncertainty estimation for non-independent node-level predictions is under-explored. In this work, we explore uncertainty quantification for node classification in three ways: (1) We derive three axioms explicitly characterizing the expected predictive uncertainty behavior in homophilic attributed graphs. (2) We propose a new model Graph Posterior Network (GPN) which explicitly performs Bayesian posterior updates for predictions on interdependent nodes. GPN provably obeys the proposed axioms. (3) We extensively evaluate GPN and a strong set of baselines on semi-supervised node classification including detection of anomalous features, and detection of left-out classes. GPN outperforms existing approaches for uncertainty estimation in the experiments.

Original language	English
Title of host publication	Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021
Editors	Marc'Aurelio Ranzato, Alina Beygelzimer, Yann Dauphin, Percy S. Liang, Jenn Wortman Vaughan
Publisher	Neural information processing systems foundation
Pages	18033-18048
Number of pages	16
ISBN (Electronic)	9781713845393
State	Published - 2021
Event	35th Conference on Neural Information Processing Systems, NeurIPS 2021 - Virtual, Online Duration: 6 Dec 2021 → 14 Dec 2021

Publication series

Name	Advances in Neural Information Processing Systems
Volume	22
ISSN (Print)	1049-5258

Conference

Conference	35th Conference on Neural Information Processing Systems, NeurIPS 2021
City	Virtual, Online
Period	6/12/21 → 14/12/21

Cite this

Stadler, M., Charpentier, B., Geisler, S., Zügner, D., & Günnemann, S. (2021). Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification. In MA. Ranzato, A. Beygelzimer, Y. Dauphin, P. S. Liang, & J. Wortman Vaughan (Eds.), Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021 (pp. 18033-18048). (Advances in Neural Information Processing Systems; Vol. 22). Neural information processing systems foundation.

Stadler, Maximilian ; Charpentier, Bertrand ; Geisler, Simon et al. / Graph Posterior Network : Bayesian Predictive Uncertainty for Node Classification. Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021. editor / Marc'Aurelio Ranzato ; Alina Beygelzimer ; Yann Dauphin ; Percy S. Liang ; Jenn Wortman Vaughan. Neural information processing systems foundation, 2021. pp. 18033-18048 (Advances in Neural Information Processing Systems).

@inproceedings{5fb801a799ca4afb92de4dfde523c9c8,

title = "Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification",

abstract = "The interdependence between nodes in graphs is key to improve class predictions on nodes and utilized in approaches like Label Propagation (LP) or in Graph Neural Networks (GNNs). Nonetheless, uncertainty estimation for non-independent node-level predictions is under-explored. In this work, we explore uncertainty quantification for node classification in three ways: (1) We derive three axioms explicitly characterizing the expected predictive uncertainty behavior in homophilic attributed graphs. (2) We propose a new model Graph Posterior Network (GPN) which explicitly performs Bayesian posterior updates for predictions on interdependent nodes. GPN provably obeys the proposed axioms. (3) We extensively evaluate GPN and a strong set of baselines on semi-supervised node classification including detection of anomalous features, and detection of left-out classes. GPN outperforms existing approaches for uncertainty estimation in the experiments.",

author = "Maximilian Stadler and Bertrand Charpentier and Simon Geisler and Daniel Z{\"u}gner and Stephan G{\"u}nnemann",

note = "Publisher Copyright: {\textcopyright} 2021 Neural information processing systems foundation. All rights reserved.; 35th Conference on Neural Information Processing Systems, NeurIPS 2021 ; Conference date: 06-12-2021 Through 14-12-2021",

year = "2021",

language = "English",

series = "Advances in Neural Information Processing Systems",

publisher = "Neural information processing systems foundation",

pages = "18033--18048",

editor = "Marc'Aurelio Ranzato and Alina Beygelzimer and Yann Dauphin and Liang, {Percy S.} and {Wortman Vaughan}, Jenn",

booktitle = "Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021",

}

Stadler, M, Charpentier, B, Geisler, S, Zügner, D & Günnemann, S 2021, Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification. in MA Ranzato, A Beygelzimer, Y Dauphin, PS Liang & J Wortman Vaughan (eds), Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021. Advances in Neural Information Processing Systems, vol. 22, Neural information processing systems foundation, pp. 18033-18048, 35th Conference on Neural Information Processing Systems, NeurIPS 2021, Virtual, Online, 6/12/21.

Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification. / Stadler, Maximilian; Charpentier, Bertrand; Geisler, Simon et al.
Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021. ed. / Marc'Aurelio Ranzato; Alina Beygelzimer; Yann Dauphin; Percy S. Liang; Jenn Wortman Vaughan. Neural information processing systems foundation, 2021. p. 18033-18048 (Advances in Neural Information Processing Systems; Vol. 22).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Graph Posterior Network

T2 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021

AU - Stadler, Maximilian

AU - Charpentier, Bertrand

AU - Geisler, Simon

AU - Zügner, Daniel

AU - Günnemann, Stephan

PY - 2021

Y1 - 2021

N2 - The interdependence between nodes in graphs is key to improve class predictions on nodes and utilized in approaches like Label Propagation (LP) or in Graph Neural Networks (GNNs). Nonetheless, uncertainty estimation for non-independent node-level predictions is under-explored. In this work, we explore uncertainty quantification for node classification in three ways: (1) We derive three axioms explicitly characterizing the expected predictive uncertainty behavior in homophilic attributed graphs. (2) We propose a new model Graph Posterior Network (GPN) which explicitly performs Bayesian posterior updates for predictions on interdependent nodes. GPN provably obeys the proposed axioms. (3) We extensively evaluate GPN and a strong set of baselines on semi-supervised node classification including detection of anomalous features, and detection of left-out classes. GPN outperforms existing approaches for uncertainty estimation in the experiments.

AB - The interdependence between nodes in graphs is key to improve class predictions on nodes and utilized in approaches like Label Propagation (LP) or in Graph Neural Networks (GNNs). Nonetheless, uncertainty estimation for non-independent node-level predictions is under-explored. In this work, we explore uncertainty quantification for node classification in three ways: (1) We derive three axioms explicitly characterizing the expected predictive uncertainty behavior in homophilic attributed graphs. (2) We propose a new model Graph Posterior Network (GPN) which explicitly performs Bayesian posterior updates for predictions on interdependent nodes. GPN provably obeys the proposed axioms. (3) We extensively evaluate GPN and a strong set of baselines on semi-supervised node classification including detection of anomalous features, and detection of left-out classes. GPN outperforms existing approaches for uncertainty estimation in the experiments.

UR - http://www.scopus.com/inward/record.url?scp=85128443901&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85128443901

T3 - Advances in Neural Information Processing Systems

SP - 18033

EP - 18048

BT - Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021

A2 - Ranzato, Marc'Aurelio

A2 - Beygelzimer, Alina

A2 - Dauphin, Yann

A2 - Liang, Percy S.

A2 - Wortman Vaughan, Jenn

PB - Neural information processing systems foundation

Y2 - 6 December 2021 through 14 December 2021

ER -

Stadler M, Charpentier B, Geisler S, Zügner D, Günnemann S. Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification. In Ranzato MA, Beygelzimer A, Dauphin Y, Liang PS, Wortman Vaughan J, editors, Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021. Neural information processing systems foundation. 2021. p. 18033-18048. (Advances in Neural Information Processing Systems).

Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification

Abstract

Publication series

Conference

Other files and links

Fingerprint

Cite this