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...
Hlavní autoři: | Saha, A, Mendez, O, Russell, C, Bowden, R |
---|---|
Médium: | Conference item |
Jazyk: | English |
Vydáno: |
IEEE
2024
|
Podobné jednotky
-
Graph Convolutional Network with Adaptive Fusion of Neighborhood Aggregation and Interaction
Autor: FU Kun, ZHUO Jiaming, GUO Yunpeng, LI Jianing, LIU Qi
Vydáno: (2023-02-01) -
Path-Neighborhood Graphs
Autor: Laskar R.C., a další
Vydáno: (2013-09-01) -
ATPGNN: Reconstruction of Neighborhood in Graph Neural Networks With Attention-Based Topological Patterns
Autor: Kehao Wang, a další
Vydáno: (2021-01-01) -
GRAPH NEURAL NETWORK BASED OPEN-SET DOMAIN ADAPTATION
Autor: S. Zhao, a další
Vydáno: (2022-05-01) -
Sequence-Aware Graph Neural Network Incorporating Neighborhood Information for Session-Based Recommendation
Autor: Liya Huang, a další
Vydáno: (2024-02-01)