Self-Supervised Node Classification with Strategy and Actively Selected Labeled Set.

Self-Supervised Node Classification with Strategy and Actively Selected Labeled Set.
复制标题

DOI:
10.3390/e25010030
复制
发表时间:
2022-12-23
期刊:
Entropy (Basel, Switzerland)
影响因子:
--
通讯作者:
--
中科院分区:
其他
文献类型:
--
作者:

文献摘要

参考文献

相似文献

为了减轻标签不足对少标签分类问题的影响,自监督学习通过关注未标记节点的信息来提高图神经网络(GNN)的性能。然而,现有的自监督借口任务在不同的数据集上都没有最佳表现,并且在组合自监督和监督任务时还包括超参数的选择。为了在不需要专家经验的情况下为每个数据集选择性能最好的自监督借口任务并优化超参数,我们提出了一种新的自图自监督学习框架,并使用一次性主动学习方法增强了该框架。在三个真实的引文数据集上的实验结果表明,使用自动优化的借口任务训练GNN可以达到甚至超过手动设计的借口任务所获得的分类准确率。在此基础上,与使用随机选择的标记节点相比,使用主动选择的标记节点可以进一步提高GNN的分类性能。主动选择和自动优化都有助于半监督节点分类。
To alleviate the impact of insufficient labels in less-labeled classification problems, self-supervised learning improves the performance of graph neural networks (GNNs) by focusing on the information of unlabeled nodes. However, none of the existing self-supervised pretext tasks perform optimally on different datasets, and the choice of hyperparameters is also included when combining self-supervised and supervised tasks. To select the best-performing self-supervised pretext task for each dataset and optimize the hyperparameters with no expert experience needed, we propose a novel auto graph self-supervised learning framework and enhance this framework with a one-shot active learning method. Experimental results on three real world citation datasets show that training GNNs with automatically optimized pretext tasks can achieve or even surpass the classification accuracy obtained with manually designed pretext tasks. On this basis, compared with using randomly selected labeled nodes, using actively selected labeled nodes can further improve the classification performance of GNNs. Both the active selection and the automatic optimization contribute to semi-supervised node classification.
DOI: 10.1016/j.knosys.2020.106622
发表时间: 2021-01-05
影响因子: 8.8
作者:
He, Xin;Zhao, Kaiyong;Chu, Xiaowen
通讯作者: Chu, Xiaowen
DOI: 10.1007/s42979-021-00815-1
发表时间: 2021
期刊: SN computer science
影响因子: --
作者:
Sarker IH
通讯作者: Sarker IH
DOI: 10.1016/j.patrec.2021.04.021
发表时间: 2021-05-24
影响因子: 5.1
作者:
Manessi, Franco;Rozza, Alessandro
通讯作者: Rozza, Alessandro
DOI: 10.3390/e22101164
发表时间: 2020-10-16
期刊: Entropy (Basel, Switzerland)
影响因子: --
作者:
Madhawa K;Murata T
通讯作者: Murata T
DOI: 10.1109/tkde.2018.2807452
发表时间: 2018-09-01
影响因子: 8.9
作者:
Cai, HongYun;Zheng, Vincent W.;Chang, Kevin Chen-Chuan
通讯作者: Chang, Kevin Chen-Chuan