Entropy-aware self-training for graph convolutional networks

Gongpei Zhao; Tao Wang; Yidong Li; Yi Jin; Congyan Lang

doi:10.1016/j.neucom.2021.08.092

ScienceGate Book Chapters

JOURNAL ARTICLE

Entropy-aware self-training for graph convolutional networks

Gongpei Zhao Tao Wang Yidong Li Yi Jin Congyan Lang

Year: 2021 Journal: Neurocomputing Vol: 464 Pages: 394-407 Publisher: Elsevier BV

DOI: 10.1016/j.neucom.2021.08.092

Get Full-Text PDF Get Analytical Report

Keywords:

Computer science Graph Entropy (arrow of time) Machine learning Artificial intelligence Random walk Theoretical computer science Cross entropy Principle of maximum entropy Mathematics

Metrics

Cited By

0.85

FWCI (Field Weighted Citation Impact)

Refs

0.78

Citation Normalized Percentile

Is in top 1%

Is in top 10%

Citation History

Topics

Advanced Graph Neural Networks

Physical Sciences → Computer Science → Artificial Intelligence

Complex Network Analysis Techniques

Physical Sciences → Physics and Astronomy → Statistical and Nonlinear Physics

Recommender Systems and Techniques

Physical Sciences → Computer Science → Information Systems

Entropy-aware self-training for graph convolutional networks

Metrics

Citation History

Topics

Related Documents

Label-Aware Graph Convolutional Networks

Deepwalk-aware graph convolutional networks

Rank-based self-training for graph convolutional networks

Joint CPU-FPGA Hardware-Aware Quantized Training of Graph Convolutional Networks

RegionGCN: Spatial-Heterogeneity-Aware Graph Convolutional Networks