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...
主要な著者: | Frasca, F, Bevilacqua, B, Bronstein, M, Maron, H |
---|---|
フォーマット: | Conference item |
言語: | English |
出版事項: |
Curran Associates
2022
|
類似資料
-
How does over-squashing affect the power of GNNs?
著者:: Di Giovanni, F, 等
出版事項: (2024) -
Neural sheaf diffusion: a topological perspective on heterophily and oversmoothing in GNNs
著者:: Bodnar, C, 等
出版事項: (2023) -
From Graph Theory to Graph Neural Networks (GNNs): The Opportunities of GNNs in Power Electronics
著者:: Yuzhuo Li, 等
出版事項: (2023-01-01) -
Learning Augmentation for GNNs With Consistency Regularization
著者:: Hyeonjin Park, 等
出版事項: (2021-01-01) -
On the correspondence between monotonic max-sum GNNs and datalog
著者:: Tena Cucala, D, 等
出版事項: (2023)