A noise-resistant graph neural network by semi-supervised contrastive learning-Reference-Cited by-同舟云学术

A noise-resistant graph neural network by semi-supervised contrastive learning

Published:2024-02 Issue: Volume:658 Page:120001
ISSN:0020-0255
Container-title:Information Sciences
language:en
Short-container-title:Information Sciences

Author:

Lu Zhengyu^ORCID,Ma Junbo,Wu Zongqian,Zhou Bo^ORCID,Zhu Xiaofeng

Publisher

Elsevier BV

Subject

Artificial Intelligence,Information Systems and Management,Computer Science Applications,Theoretical Computer Science,Control and Systems Engineering,Software

Reference48 articles.

1. Nrgnn: learning a label noise resistant graph neural network on sparsely and noisily labeled graphs;Dai,2021

2. Convolutional neural networks on graphs with fast localized spectral filtering;Defferrard;Adv. Neural Inf. Process. Syst.,2016

3. Multi-graph fusion for dynamic graph convolutional network;Gan;IEEE Trans. Neural Netw. Learn. Syst.,2022

Cited by 5 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Dismantling complex networks with graph contrastive learning and multi-hop aggregation;Information Sciences;2024-08

2. Multi-view fair-augmentation contrastive graph clustering with reliable pseudo-labels;Information Sciences;2024-07

3. Noise-resistant graph neural networks with manifold consistency and label consistency;Expert Systems with Applications;2024-07

4. Neural collapse inspired semi-supervised learning with fixed classifier;Information Sciences;2024-05

5. An imbalanced contrastive classification method via similarity comparison within sample-neighbors with adaptive generation coefficient;Information Sciences;2024-03