Higher-Order Graph Convolutional Networks With Multi-Scale Neighborhood Pooling for Semi-Supervised Node Classification
| Autor: | Shihui Chang, Xun Liu, Yikuan Zhang, Guoqing Xia, Fangyuan Lei |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
General Computer Science
Computational complexity theory Computer science Pooling Scale (descriptive set theory) 02 engineering and technology computer.software_genre High-order convolution Convolution 020204 information systems weight sharing 0202 electrical engineering electronic engineering information engineering General Materials Science Electrical and Electronic Engineering semi-supervised node classification Node (networking) Aggregate (data warehouse) General Engineering Graph higher-order graph convolutional network Feature (computer vision) Graph (abstract data type) 020201 artificial intelligence & image processing graph convolutional networks lcsh:Electrical engineering. Electronics. Nuclear engineering Data mining multi-scale neighborhood pooling lcsh:TK1-9971 computer |
| Zdroj: | IEEE Access, Vol 9, Pp 31268-31275 (2021) |
| ISSN: | 2169-3536 |
| Popis: | Existing popular methods for semi-supervised node classification with high-order convolution improve the learning ability of graph convolutional networks (GCNs) by capturing the feature information from high-order neighborhoods. However, these methods with high-order convolution usually require many parameters and high computational complexity. To address these limitations, we propose HCNP, a new higher-order GCN for semi-supervised node learning tasks, which can simultaneously aggregate information of various neighborhoods by constructing high-order convolution. In HCNP, we reduce the number of parameters using a weight sharing mechanism and combine the neighborhood information via multi-scale neighborhood pooling. Further, HCNP does not require a large number of hidden units, and it fits a few parameters and exhibits low complexity. We show that HCNP matches GCNs in terms of complexity and parameters. Comprehensive evaluations on publication citation datasets (Citeseer, Pubmed, and Cora) demonstrate that the proposed methods outperform MixHop in most cases while maintaining lower complexity and fewer parameters and achieve state-of-the-art performance in terms of accuracy and parameters compared to other baselines. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|