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...
Главные авторы: | Frasca, F, Bevilacqua, B, Bronstein, M, Maron, H |
---|---|
Формат: | Conference item |
Язык: | English |
Опубликовано: |
Curran Associates
2022
|
Схожие документы
-
How does over-squashing affect the power of GNNs?
по: Di Giovanni, F, и др.
Опубликовано: (2024) -
Neural sheaf diffusion: a topological perspective on heterophily and oversmoothing in GNNs
по: Bodnar, C, и др.
Опубликовано: (2023) -
From Graph Theory to Graph Neural Networks (GNNs): The Opportunities of GNNs in Power Electronics
по: Yuzhuo Li, и др.
Опубликовано: (2023-01-01) -
Learning Augmentation for GNNs With Consistency Regularization
по: Hyeonjin Park, и др.
Опубликовано: (2021-01-01) -
On the correspondence between monotonic max-sum GNNs and datalog
по: Tena Cucala, D, и др.
Опубликовано: (2023)