arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.14159cs.LG
收藏

自适应多层对比图神经网络

Adaptive Multi-layer Contrastive Graph Neural Networks

PLA Strategy Support Force Information Engineering University(中国人民解放军战略支援部队信息工程大学)

Shuhao Shi, Pengfei Xie, Xu Luo, Kai Qiao, Linyuan Wang, Jian Chen, Bin Yan

AI总结:

本文提出自适应多层对比图神经网络AMC-GNN,通过注意力机制自适应融合多层嵌入并引入辅助编码器进行自监督对比学习,在多个图基准数据集上持续提升分类准确率。

摘要:

我们提出自适应多层对比图神经网络(AMC-GNN),这是一种用于图神经网络的自监督学习框架,可在没有数据标签的情况下学习样本数据的特征表示。AMC-GNN通过数据增强生成两个图视图,并比较图神经网络编码器不同层的输出嵌入以获得特征表示,这些表示可用于下游任务。AMC-GNN能够通过注意力机制自适应地学习不同层中嵌入的重要性权重,并引入辅助编码器以更好地训练图对比编码器。通过最大化早期层和最终嵌入空间中正样本对表示的一致性来提高准确率。我们的实验表明,使用AMC-GNN框架可以在四个已建立的图基准上持续改进结果:Cora、Citeseer、Pubmed、DBLP引文网络数据集,以及四个新提出的数据集:Co-author-CS、Co-author-Physics、Amazon-Computers、Amazon-Photo。

英文摘要:

We present Adaptive Multi-layer Contrastive Graph Neural Networks (AMC-GNN), a self-supervised learning framework for Graph Neural Network, which learns feature representations of sample data without data labels. AMC-GNN generates two graph views by data augmentation and compares different layers' output embeddings of Graph Neural Network encoders to obtain feature representations, which could be used for downstream tasks. AMC-GNN could learn the importance weights of embeddings in different layers adaptively through the attention mechanism, and an auxiliary encoder is introduced to train graph contrastive encoders better. The accuracy is improved by maximizing the representation's consistency of positive pairs in the early layers and the final embedding space. Our experiments show that the results can be consistently improved by using the AMC-GNN framework, across four established graph benchmarks: Cora, Citeseer, Pubmed, DBLP citation network datasets, as well as four newly proposed datasets: Co-author-CS, Co-author-Physics, Amazon-Computers, Amazon-Photo.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑