Union subgraph neural networks
Graph Neural Networks (GNNs) are widely used for graph representation learning in many application domains. The expressiveness of vanilla GNNs is upper-bounded by 1-dimensional Weisfeiler-Leman (1-WL) test as they operate on rooted subtrees through iterative message passing. In this paper, we empowe...
Main Authors: | Xu, Jiaxing, Zhang, Aihu, Bian, Qingtian, Dwivedi, Vijay Prakash, Ke, Yiping |
---|---|
Other Authors: | School of Computer Science and Engineering |
Format: | Conference Paper |
Language: | English |
Published: |
2024
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/173329 https://ojs.aaai.org/index.php/AAAI/article/view/29551 |
Similar Items
-
Mathematical Expressiveness of Graph Neural Networks
by: Guillaume Lachaud, et al.
Published: (2022-12-01) -
Polarized message-passing in graph neural networks
by: He, Tiantian, et al.
Published: (2024) -
Beyond Weisfeiler–Lehman with Local Ego-Network Encodings
by: Nurudin Alvarez-Gonzalez, et al.
Published: (2023-09-01) -
DAG: Dual Attention Graph Representation Learning for Node Classification
by: Siyi Lin, et al.
Published: (2023-08-01) -
Dynamic graph neural network with adaptive edge attributes for air quality prediction: A case study in China
by: Jing Xu, et al.
Published: (2023-07-01)