Graph convolutional networks for graphs containing missing features
Authors:
- Hibiki TaguchiHTHibiki Taguchi
- Xin LiuXLXin Liu
- Tsuyoshi MurataTMTsuyoshi Murata
Open Access
- 1 April 2021
- journal article
- research article
- Published by Elsevier in Future Generation Computer Systems
- Vol. 117, 155-168
Abstract
No abstract availableKeywords
All Related Versions
Funding Information
- Japan Science and Technology Agency
- Japan Society for the Promotion of Science
- New Energy and Industrial Technology Development Organization
This publication has 41 references indexed in Scilit:
- Knowledge Graph Embedding: A Survey of Approaches and ApplicationsIEEE Transactions on Knowledge and Data Engineering, 2017
- Structural Deep Network Embedding2016
- Image-Based Recommendations on Styles and Substitutes2015
- LINE2015
- DeepWalk2014
- MissForest—non-parametric missing value imputation for mixed-type dataBioinformatics, 2011
- Pattern classification with missing data: a reviewNeural Computing and Applications, 2009
- The Graph Neural Network ModelIEEE Transactions on Neural Networks, 2008
- Collective Classification in Network DataAI Magazine, 2008
- Handling missing values in support vector machine classifiersNeural Networks, 2005