English
 
Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
 Local TagsRelease HistoryDetailsSummary
  Dirac-Bianconi Graph Neural Networks - Enabling Non-Diffusive Long-Range Graph Predictions

Nauck, C., Gorantla, R., Lindner, M., Schürholt, K., Mey, A. S. J. S., Hellmann, F. (2024): Dirac-Bianconi Graph Neural Networks - Enabling Non-Diffusive Long-Range Graph Predictions, (Proceedings of Machine Learning Research ; 251).

Item is

 

show all hide all

Basic

show hide
Item Permalink: https://publications.pik-potsdam.de/pubman/item/item_30045 Version Permalink: https://publications.pik-potsdam.de/pubman/item/item_30045_1
Genre: Other

Files

show Files
hide Files
:
Nauck_DBGNN-16.pdf (Any fulltext), 5MB
View   Save
File Permalink:
https://publications.pik-potsdam.de/pubman/item/item_30045_1/component/file_30046/Nauck_DBGNN-16.pdf
Name:
Nauck_DBGNN-16.pdf
Description:
-
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
View
Copyright Date:
-
Copyright Info:
-
License:
https://creativecommons.org/licenses/by/4.0/

Locators

show
hide
Locator:
https://openreview.net/forum?id=mZzE0xh1QW (Publisher version)
Description:
-
Locator:
https://doi.org/10.48550/arXiv.2407.12419 (Preprint)
Description:
-

Creators

show
hide
 Creators:
Nauck, Christian1, Author              
Gorantla, Rohan 2, Author
Lindner, Michael1, Author              
Schürholt, Konstantin 2, Author
Mey, Antonia S. J. S. 2, Author
Hellmann, Frank1, Author              
Affiliations:
1Potsdam Institute for Climate Impact Research, ou_persistent13              
2External Organizations, ou_persistent22              

Content

show
hide
Free keywords: -
 Abstract: The geometry of a graph is encoded in dynamical processes on the graph. Many graph neural network (GNN) architectures are inspired by such dynamical systems, typically based on the graph Laplacian. Here, we introduce Dirac--Bianconi GNNs (DBGNNs), which are based on the topological Dirac equation recently proposed by Bianconi. Based on the graph Laplacian, we demonstrate that DBGNNs explore the geometry of the graph in a fundamentally different way than conventional message passing neural networks (MPNNs). While regular MPNNs propagate features diffusively, analogous to the heat equation, DBGNNs allow for coherent long-range propagation. Experimental results showcase the superior performance of DBGNNs over existing conventional MPNNs for long-range predictions of power grid stability and peptide properties. This study highlights the effectiveness of DBGNNs in capturing intricate graph dynamics, providing notable advancements in GNN architectures.

Details

show
hide
Language(s): eng - English
 Dates: 2024-07-232024-06-182024-08-21
 Publication Status: Finally published
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: Peer
 Identifiers: PIKDOMAIN: RD4 - Complexity Science
Organisational keyword: RD4 - Complexity Science
Working Group: Dynamics, stability and resilience of complex hybrid infrastructure networks
Research topic keyword: Energy
Model / method: Machine Learning
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: Proceedings of Machine Learning Research
Source Genre: Series
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: 251 Sequence Number: - Start / End Page: - Identifier: -