Back
von-rohrscheidt25a
Journal article

Diss-l-ECT: Dissecting Graph Data with Local Euler Characteristic Transforms

BP2-STS

  • 2025
Published in:
  • Proceedings of the 42nd International Conference on Machine Learning. - Vancouver Convention Center, Vancouver, Canada. - 2025, vol. PMLR 267, p. 61790-61809
topological data analysis
topological deep learning
geometric deep learning
euler characteristic transform
euler characteristic
English The Euler Characteristic Transform (ECT) is an efficiently computable geometrical-topological invariant that characterizes the global shape of data. In this paper, we introduce the local Euler Characteristic Transform (ℓ-ECT), a novel extension of the ECT designed to enhance expressivity and interpretability in graph representation learning. Unlike traditional Graph Neural Networks (GNNs), which may lose critical local details through aggregation, the ℓ-ECT provides a lossless representation of local neighborhoods. This approach addresses key limitations in GNNs by preserving nuanced local structures while maintaining global interpretability. Moreover, we construct a rotation-invariant metric based on ℓ-ECTs for spatial alignment of data spaces. Our method demonstrates superior performance compared to standard GNNs on various benchmarking node classification tasks, while also offering theoretical guarantees of its effectiveness.
Faculty
Faculté des sciences et de médecine
Department
Département d'Informatique
Language
  • English
Classification
Medicine, Technology, Engineering
Other electronic version

Published version

License
License undefined
Open access status
green
Persistent URL
https://folia.unifr.ch/unifr/documents/334092
Statistics
Document views: 24 File downloads:
  • von-rohrscheidt25a: 16