GRAND: Graph Neural Diffusion

Benjamin P. Chamberlain; James Rowbottom; Maria Gorinova; Stefan Webb; Emanuele Rossi; Michael M. Bronstein

GRAND: Graph Neural Diffusion

Benjamin P. Chamberlain^*, James Rowbottom, Maria Gorinova, Stefan Webb, Emanuele Rossi, Michael M. Bronstein

^*Corresponding author for this work

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

Abstract

We present Graph Neural Diffusion (GRAND) that approaches deep learning on graphs as a continuous diffusion process and treats Graph Neural Networks (GNNs) as discretisations of an underlying PDE. In our model, the layer structure and topology correspond to the discretisation choices of temporal and spatial operators. Our approach allows a principled development of a broad new class of GNNs that are able to address the common plights of graph learning models such as depth, oversmoothing, and bottlenecks. Key to the success of our models are stability with respect to perturbations in the data and this is addressed for both implicit and explicit discretisation schemes. We develop linear and nonlinear versions of GRAND, which achieve competitive results on many standard graph benchmarks.

Original language	English
Title of host publication	Proceedings of the 38th International Conference on Machine Learning, ICML 2021
Publisher	ML Research Press
Pages	1407-1418
Number of pages	12
ISBN (Electronic)	9781713845065
State	Published - 2021
Externally published	Yes
Event	38th International Conference on Machine Learning, ICML 2021 - Virtual, Online Duration: 18 Jul 2021 → 24 Jul 2021

Publication series

Name	Proceedings of Machine Learning Research
Volume	139
ISSN (Electronic)	2640-3498

Conference

Conference	38th International Conference on Machine Learning, ICML 2021
City	Virtual, Online
Period	18/07/21 → 24/07/21

Cite this

@inproceedings{763be7f349d14455a775ba51c213e5e8,

title = "GRAND: Graph Neural Diffusion",

abstract = "We present Graph Neural Diffusion (GRAND) that approaches deep learning on graphs as a continuous diffusion process and treats Graph Neural Networks (GNNs) as discretisations of an underlying PDE. In our model, the layer structure and topology correspond to the discretisation choices of temporal and spatial operators. Our approach allows a principled development of a broad new class of GNNs that are able to address the common plights of graph learning models such as depth, oversmoothing, and bottlenecks. Key to the success of our models are stability with respect to perturbations in the data and this is addressed for both implicit and explicit discretisation schemes. We develop linear and nonlinear versions of GRAND, which achieve competitive results on many standard graph benchmarks.",

author = "Chamberlain, {Benjamin P.} and James Rowbottom and Maria Gorinova and Stefan Webb and Emanuele Rossi and Bronstein, {Michael M.}",

note = "Publisher Copyright: Copyright {\textcopyright} 2021 by the author(s); 38th International Conference on Machine Learning, ICML 2021 ; Conference date: 18-07-2021 Through 24-07-2021",

year = "2021",

language = "אנגלית",

series = "Proceedings of Machine Learning Research",

publisher = "ML Research Press",

pages = "1407--1418",

booktitle = "Proceedings of the 38th International Conference on Machine Learning, ICML 2021",

}

Chamberlain, BP, Rowbottom, J, Gorinova, M, Webb, S, Rossi, E & Bronstein, MM 2021, GRAND: Graph Neural Diffusion. in Proceedings of the 38th International Conference on Machine Learning, ICML 2021. Proceedings of Machine Learning Research, vol. 139, ML Research Press, pp. 1407-1418, 38th International Conference on Machine Learning, ICML 2021, Virtual, Online, 18/07/21.

GRAND: Graph Neural Diffusion. / Chamberlain, Benjamin P.; Rowbottom, James; Gorinova, Maria et al.
Proceedings of the 38th International Conference on Machine Learning, ICML 2021. ML Research Press, 2021. p. 1407-1418 (Proceedings of Machine Learning Research; Vol. 139).

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

TY - GEN

T1 - GRAND

T2 - 38th International Conference on Machine Learning, ICML 2021

AU - Chamberlain, Benjamin P.

AU - Rowbottom, James

AU - Gorinova, Maria

AU - Webb, Stefan

AU - Rossi, Emanuele

AU - Bronstein, Michael M.

PY - 2021

Y1 - 2021

N2 - We present Graph Neural Diffusion (GRAND) that approaches deep learning on graphs as a continuous diffusion process and treats Graph Neural Networks (GNNs) as discretisations of an underlying PDE. In our model, the layer structure and topology correspond to the discretisation choices of temporal and spatial operators. Our approach allows a principled development of a broad new class of GNNs that are able to address the common plights of graph learning models such as depth, oversmoothing, and bottlenecks. Key to the success of our models are stability with respect to perturbations in the data and this is addressed for both implicit and explicit discretisation schemes. We develop linear and nonlinear versions of GRAND, which achieve competitive results on many standard graph benchmarks.

AB - We present Graph Neural Diffusion (GRAND) that approaches deep learning on graphs as a continuous diffusion process and treats Graph Neural Networks (GNNs) as discretisations of an underlying PDE. In our model, the layer structure and topology correspond to the discretisation choices of temporal and spatial operators. Our approach allows a principled development of a broad new class of GNNs that are able to address the common plights of graph learning models such as depth, oversmoothing, and bottlenecks. Key to the success of our models are stability with respect to perturbations in the data and this is addressed for both implicit and explicit discretisation schemes. We develop linear and nonlinear versions of GRAND, which achieve competitive results on many standard graph benchmarks.

UR - http://www.scopus.com/inward/record.url?scp=85131640625&partnerID=8YFLogxK

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85131640625

T3 - Proceedings of Machine Learning Research

SP - 1407

EP - 1418

BT - Proceedings of the 38th International Conference on Machine Learning, ICML 2021

PB - ML Research Press

Y2 - 18 July 2021 through 24 July 2021

ER -

GRAND: Graph Neural Diffusion

Abstract

Publication series

Conference

Other files and links

Fingerprint

Cite this