Demystifying Higher-Order Graph Neural Networks
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-03 · 48 (3) · 2544-2565
DOI: 10.1109/tpami.2025.3637114 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-03. Verfasst von Maciej Besta und 6 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 185 Literaturangaben. Gefördert von: European Research Council Project PSAP, European High-Performance Computing Joint Undertaking, ETH Future Computing Laboratory.
Abstract (Originalsprache)
Higher-order graph neural networks (HOGNNs) and the related architectures from Topological Deep Learning are an important class of GNN models that harness polyadic relations between vertices beyond plain edges. They have been used to eliminate issues such as over-smoothing or over-squashing, to significantly enhance the accuracy of GNN predictions, to improve the expressiveness of GNN architectures, and for numerous other goals. A plethora of HOGNN models have been introduced, and they come with diverse neural architectures, and even with different notions of what the "higher-order" means. This richness makes it very challenging to appropriately analyze and compare HOGNN models, and to decide in what scenario to use specific ones. To alleviate this, we first design an in-depth taxonomy and a blueprint for HOGNNs. This facilitates designing models that maximize performance. Then, we use our taxonomy to analyze and compare the available HOGNN models. The outcomes of our analysis are synthesized in a set of insights that help to select the most beneficial GNN model in a given scenario, and a comprehensive list of challenges and opportunities for further research into more powerful HOGNNs.
Förderung
- European Research Council Project PSAP
- European High-Performance Computing Joint Undertaking
- ETH Future Computing Laboratory
- Huawei Technologies
- European Union’s HE Research and Innovation Programme
- Polish high-performance computing infrastructure PLGrid
- Swiss AI Initiative for the computational grant
Zitieren
APA
Besta, M., Scheidl, F., Gianinazzi, L., Kwasniewski, G., Klaiman, S., Muller, J., & Hoefler, T. (2026). Demystifying Higher-Order Graph Neural Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(3), 2544-2565. https://doi.org/10.1109/tpami.2025.3637114
Vancouver
Besta M, Scheidl F, Gianinazzi L, Kwasniewski G, Klaiman S, Muller J, et al. Demystifying Higher-Order Graph Neural Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(3):2544-2565. doi:10.1109/tpami.2025.3637114
BibTeX
@article{Besta2026,
author = {Besta, Maciej and Scheidl, Florian and Gianinazzi, Lukas and Kwasniewski, Grzegorz and Klaiman, Shachar and Muller, Jurgen and Hoefler, Torsten},
title = {Demystifying Higher-Order Graph Neural Networks},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2026},
volume = {48},
number = {3},
pages = {2544--2565},
doi = {10.1109/tpami.2025.3637114}
}
EUVIMED