Understanding and extending subgraph GNNs by rethinking their symmetries
Subgraph GNNs are a recent class of expressive Graph Neural Networks (GNNs) which model graphs as collections of subgraphs. So far, the design space of possible Subgraph GNN architectures as well as their basic theoretical properties are still largely unexplored. In this paper, we study the most pro...
Autori principali: | Frasca, F, Bevilacqua, B, Bronstein, M, Maron, H |
---|---|
Natura: | Conference item |
Lingua: | English |
Pubblicazione: |
Curran Associates
2022
|
Documenti analoghi
-
How does over-squashing affect the power of GNNs?
di: Di Giovanni, F, et al.
Pubblicazione: (2024) -
Neural sheaf diffusion: a topological perspective on heterophily and oversmoothing in GNNs
di: Bodnar, C, et al.
Pubblicazione: (2023) -
From Graph Theory to Graph Neural Networks (GNNs): The Opportunities of GNNs in Power Electronics
di: Yuzhuo Li, et al.
Pubblicazione: (2023-01-01) -
Learning Augmentation for GNNs With Consistency Regularization
di: Hyeonjin Park, et al.
Pubblicazione: (2021-01-01) -
On the correspondence between monotonic max-sum GNNs and datalog
di: Tena Cucala, D, et al.
Pubblicazione: (2023)