Learning adaptive neighborhoods for graph neural networks
Graph convolutional networks (GCNs) enable end-to-end learning on graph structured data. However, many works assume a given graph structure. When the input graph is noisy or unavailable, one approach is to construct or learn a latent graph structure. These methods typically fix the choice of node de...
Autori principali: | Saha, A, Mendez, O, Russell, C, Bowden, R |
---|---|
Natura: | Conference item |
Lingua: | English |
Pubblicazione: |
IEEE
2024
|
Documenti analoghi
-
Graph Convolutional Network with Adaptive Fusion of Neighborhood Aggregation and Interaction
di: FU Kun, ZHUO Jiaming, GUO Yunpeng, LI Jianing, LIU Qi
Pubblicazione: (2023-02-01) -
Path-Neighborhood Graphs
di: Laskar R.C., et al.
Pubblicazione: (2013-09-01) -
ATPGNN: Reconstruction of Neighborhood in Graph Neural Networks With Attention-Based Topological Patterns
di: Kehao Wang, et al.
Pubblicazione: (2021-01-01) -
GRAPH NEURAL NETWORK BASED OPEN-SET DOMAIN ADAPTATION
di: S. Zhao, et al.
Pubblicazione: (2022-05-01) -
Sequence-Aware Graph Neural Network Incorporating Neighborhood Information for Session-Based Recommendation
di: Liya Huang, et al.
Pubblicazione: (2024-02-01)