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...
Những tác giả chính: | Frasca, F, Bevilacqua, B, Bronstein, M, Maron, H |
---|---|
Định dạng: | Conference item |
Ngôn ngữ: | English |
Được phát hành: |
Curran Associates
2022
|
Những quyển sách tương tự
-
How does over-squashing affect the power of GNNs?
Bằng: Di Giovanni, F, et al.
Được phát hành: (2024) -
Neural sheaf diffusion: a topological perspective on heterophily and oversmoothing in GNNs
Bằng: Bodnar, C, et al.
Được phát hành: (2023) -
From Graph Theory to Graph Neural Networks (GNNs): The Opportunities of GNNs in Power Electronics
Bằng: Yuzhuo Li, et al.
Được phát hành: (2023-01-01) -
Learning Augmentation for GNNs With Consistency Regularization
Bằng: Hyeonjin Park, et al.
Được phát hành: (2021-01-01) -
On the correspondence between monotonic max-sum GNNs and datalog
Bằng: Tena Cucala, D, et al.
Được phát hành: (2023)