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...
Autors principals: | Frasca, F, Bevilacqua, B, Bronstein, M, Maron, H |
---|---|
Format: | Conference item |
Idioma: | English |
Publicat: |
Curran Associates
2022
|
Ítems similars
-
How does over-squashing affect the power of GNNs?
per: Di Giovanni, F, et al.
Publicat: (2024) -
Neural sheaf diffusion: a topological perspective on heterophily and oversmoothing in GNNs
per: Bodnar, C, et al.
Publicat: (2023) -
From Graph Theory to Graph Neural Networks (GNNs): The Opportunities of GNNs in Power Electronics
per: Yuzhuo Li, et al.
Publicat: (2023-01-01) -
Learning Augmentation for GNNs With Consistency Regularization
per: Hyeonjin Park, et al.
Publicat: (2021-01-01) -
On the correspondence between monotonic max-sum GNNs and datalog
per: Tena Cucala, D, et al.
Publicat: (2023)