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