SkillAgentSearch skills...

SWAN

Official reference implementation of our paper "On Oversquashing in Graph Neural Networks Through The Lens of Dynamical Systems" accepted at AAAI 2025

Install / Use

/learn @gravins/SWAN
About this skill

Quality Score

0/100

Supported Platforms

Universal

README

SWAN

Official reference implementation of our paper On Oversquashing in Graph Neural Networks Through The Lens of Dynamical Systems accepted at AAAI 2025.

Please consider citing us

@inproceedings{gravina2025swan,
	title={{On Oversquashing in Graph Neural Networks Through The Lens of Dynamical Systems}},
	author={Alessio Gravina and Moshe Eliasof and Claudio Gallicchio and Davide Bacciu and Carola-Bibiane Sch\"onlieb},
	booktitle={The 39th Annual AAAI Conference on Artificial Intelligence},
	year={2025},
	month={Apr.}, 
	pages={16906-16914},
	volume={39}, 
	DOI={10.1609/aaai.v39i16.33858}, 
	number={16} 
}

Run the experiments

To reproduce the experiments please refer to:

graph_property_prediction/README.md to run the diameter, SSSP, and eccentricity experiments. graph_transfer/README.md to run the graph transfer tasks on line, ring, and crossed-ring topologies.

View on GitHub
GitHub Stars10
CategoryDevelopment
Updated8mo ago
Forks1

Languages

Python

Security Score

67/100

Audited on Aug 8, 2025

No findings