NGAT：基于广度和深度探索注意力机制的半监督图表示学习

胡荐苛; 张引

doi:10.1631/FITEE.2000657

Your Location：

Home >

Browse articles >

NGAT：基于广度和深度探索注意力机制的半监督图表示学习

常规文章 | Updated：2022-03-28

- NGAT：基于广度和深度探索注意力机制的半监督图表示学习
  Enhanced Publication
- NGAT: attention in breadth and depth exploration for semi-supervised graph representation learning
- 信息与电子工程前沿（英文） 2022年23卷第3期页码：409-421
- Affiliations：
  
  College of Computer Science and Technology, Zhejiang University, Hangzhou310027, China
- Author bio：
  
  ‡Corresponding author
- Funds：
  
  China Knowledge Centre for Engineering Sciences and Technology (CKCEST)
- DOI：10.1631/FITEE.2000657
  中图分类号： TP391
- 收稿：2020-11-22，
  
  录用：2021-01-10，
  
  网络出版：2022-01-24，
  
  纸质出版：2022-03-0
- Accepted：
Scan QR Code
胡荐苛, 张引. NGAT：基于广度和深度探索注意力机制的半监督图表示学习[J]. 信息与电子工程前沿（英文）, 2022,23(3):409-421.

Jianke HU, Yin ZHANG. NGAT: attention in breadth and depth exploration for semi-supervised graph representation learning[J]. Frontiers of Information Technology & Electronic Engineering, 2022, 23(3): 409-421.
胡荐苛, 张引. NGAT：基于广度和深度探索注意力机制的半监督图表示学习[J]. 信息与电子工程前沿（英文）, 2022,23(3):409-421. DOI： 10.1631/FITEE.2000657.

Jianke HU, Yin ZHANG. NGAT: attention in breadth and depth exploration for semi-supervised graph representation learning[J]. Frontiers of Information Technology & Electronic Engineering, 2022, 23(3): 409-421. DOI： 10.1631/FITEE.2000657.

摘要

近年来图神经网络（GNN）在图结构数据表示学习方面取得显著成绩。然而，随着网络层数增加，由于过度平滑问题，基于邻域信息聚合策略的GNN性能恶化，这也是GNN应用于真实图的主要瓶颈。研究人员对直连节点的特征信息聚合过程进行了许多改进，即广度探索。然而，这些模型仅在层数为3或更少的情况下才表现最佳，而在深层情况下性能迅速下降。为缓解过度平滑，本文提出一种嵌套的图注意网络，即基于双重注意力机制的多尺度特征融合模型NGAT，该网络可以半监督形式工作。除广度探索，

层NGAT运用注意力机制引导的分层聚合策略，选择性地利用来自

阶邻域的信息特征，即深度探索。即使对于10层或更深的架构，NGAT也能平衡保留局部性（包括根节点特征和局部结构）和从大型邻域聚合信息的需求。本文在公开数据集上对比了现有图神经网络模型，实验表明本文提出的NGAT模型具备更强的节点嵌入学习能力。

Abstract

Recently

graph neural networks (GNNs) have achieved remarkable performance in representation learning on graph-structured data. However

as the number of network layers increases

GNNs based on the neighborhood aggregation strategy deteriorate due to the problem of oversmoothing

which is the major bottleneck for applying GNNs to real-world graphs. Many efforts have been made to improve the process of feature information aggregation from directly connected nodes

i.e.

breadth exploration. However

these models perform the best only in the case of three or fewer layers

and the performance drops rapidly for deep layers. To alleviate oversmoothing

we propose a nested graph attention network (NGAT)

which can work in a semi-supervised manner. In addition to breadth exploration

-layer NGAT uses a layer-wise aggregation strategy guided by the attention mechanism to selectively leverage feature information from the

-order neighborhood

i.e.

depth exploration. Even with a 10-layer or deeper architecture

NGAT can balance the need for preserving the locality (including root node features and the local structure) and aggregating the information from a large neighborhood. In a number of experiments on standard node classification tasks

NGAT outperforms other novel models and achieves state-of-the-art performance.

关键词

Keywords

references

Atwood J , Towsley D , 2016 . Diffusion-convolutional neural networks . Proc 30 th Int Conf on Neural Information Processing Systems , p. 2001 - 2009 .

Belkin M , Niyogi P , Sindhwani V , 2006 . Manifold regularization: a geometric framework for learning from labeled and unlabeled examples . J Mach Learn Res , 7 : 2399 - 2434 .

Bruna J , Zaremba W , Szlam A , et al. , 2014 . Spectral networks and locally connected networks on graphs . https://arxiv.org/abs/1312.6203 https://arxiv.org/abs/1312.6203

Buchnik E , Cohen E , 2018 . Bootstrapped graph diffusions: exposing the power of nonlinearity . Proc ACM Int Conf on Measurement and Modeling of Computer Systems , p. 8 - 10 . doi: 10.1145/3219617.3219621 http://doi.org/10.1145/3219617.3219621

Chapelle O , Scholkopf B , Zien A , 2009 . Semi-supervised learning (Chapelle, O. et al., Eds.; 2006) [book reviews] . IEEE Trans Neur Netw , 20 ( 3 ): 542 . doi: 10.1109/TNN.2009.2015974 http://doi.org/10.1109/TNN.2009.2015974

Chen J , Ma TF , Xiao C , 2018 . FastGCN: fast learning with graph convolutional networks via importance sampling . https://arxiv.org/abs/1801.10247 https://arxiv.org/abs/1801.10247

Defferrard M , Bresson X , Vandergheynst P , 2016 . Convolutional neural networks on graphs with fast localized spectral filtering . Proc 30 th Int Conf on Neural Information Processing Systems , p. 3844 - 3852 .

Grover A , Leskovec J , 2016 . node2vec: scalable feature learning for networks . Proc 22 nd ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining , p. 855 - 864 . doi: 10.1145/2939672.2939754 http://doi.org/10.1145/2939672.2939754

Hamilton WL , Ying R , Leskovec J , 2017 . Inductive representation learning on large graphs . Proc 31 st Int Conf on Neural Information Processing Systems , p. 1025 - 1035 .

He KM , Zhang XY , Ren SQ , et al. , 2016 . Deep residual learning for image recognition . Proc IEEE Conf on Computer Vision and Pattern Recognition , p. 770 - 778 . doi: 10.1109/CVPR.2016.90 http://doi.org/10.1109/CVPR.2016.90

Kingma DP , Ba J , 2014 . Adam: a method for stochastic optimization . https://arxiv.org/abs/1412.6980 https://arxiv.org/abs/1412.6980

Kipf TN , Welling M , 2017 . Semi-supervised classification with graph convolutional networks . https://arxiv.org/abs/1609.02907 https://arxiv.org/abs/1609.02907

Klicpera J , Bojchevski A , Günnemann S , 2019 . Predict then propagate: graph neural networks meet personalized pagerank . https://arxiv.org/abs/1810.05997v4 https://arxiv.org/abs/1810.05997v4

Knyazev B , Taylor GW , Amer MR , 2019 . Understanding attention and generalization in graph neural networks . Proc 33 rd Conf on Neural Information Processing Systems , p. 4204 - 4214 .

Krizhevsky A , Sutskever I , Hinton GE , 2012 . ImageNet classification with deep convolutional neural networks . Proc 25 th Int Conf on Neural Information Processing Systems , p. 1097 - 1105 .

Lee J , Lee I , Kang J , 2019 . Self-attention graph pooling . https://arxiv.org/abs/1904.08082 https://arxiv.org/abs/1904.08082

Li QM , Han ZC , Wu XM , 2018 . Deeper insights into graph convolutional networks for semi-supervised learning . Proc 32 nd AAAI Conf on Artificial Intelligence , p. 3538 - 3545 .

Liao RJ , Zhao ZZ , Urtasun R , et al. , 2019 . LanczosNet: multi-scale deep graph convolutional networks . https://arxiv.org/abs/1901.01484v1 https://arxiv.org/abs/1901.01484v1

Namata G , London B , Getoor L , et al. , 2012 . Query-driven active surveying for collective classification . Proc 10 th Int Workshop on Mining and Learning with Graphs , Article 8 .

Niepert M , Ahmed M , Kutzkov K , 2016 . Learning convolutional neural networks for graphs . Proc 33 rd Int Conf on Machine Learning , p. 2014 - 2023 .

Perozzi B , Al-Rfou R , Skiena S , 2014 . DeepWalk: online learning of social representations . Proc 20 th ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining , p. 701 - 710 . doi: 10.1145/2623330.2623732 http://doi.org/10.1145/2623330.2623732

Ribeiro LFR , Saverese PHP , Figueiredo DR , 2017 . struc2vec: learning node representations from structural identity . Proc 23 rd ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining , p. 385 - 394 . doi: 10.1145/3097983.3098061 http://doi.org/10.1145/3097983.3098061

Sen P , Namata G , Bilgic M , et al. , 2008 . Collective classification in network data . AI Mag , 29 ( 3 ): 93 . doi: 10.1609/aimag.v29i3.2157 http://doi.org/10.1609/aimag.v29i3.2157

Shchur O , Mumme M , Bojchevski A , et al. , 2018 . Pitfalls of graph neural network evaluation . https://arxiv.org/abs/1811.05868 https://arxiv.org/abs/1811.05868

Simonyan K , Zisserman A , 2014 . Very deep convolutional networks for large-scale image recognition . https://arxiv.org/abs/1409.1556 https://arxiv.org/abs/1409.1556

Srivastava N , Hinton G , Krizhevsky A , et al. , 2014 . Dropout: a simple way to prevent neural networks from overfitting . J Mach Learn Res , 15 ( 1 ): 1929 - 1958 .

Thekumparampil KK , Wang C , Oh S , et al. , 2018 . Attention-based graph neural network for semi-supervised learning . https://arxiv.org/abs/1803.03735 https://arxiv.org/abs/1803.03735

van der Maaten L , Hinton G , 2008 . Visualizing data using t-SNE . J Mach Learn Res , 9 : 2579 - 2605 .

Vaswani A , Shazeer N , Parmar N , et al. , 2017 . Attention is all you need . Proc 31 st Int Conf on Neural Information Processing Systems , p. 6000 - 6010 .

Veličković P , Cucurull G , Casanova A , et al. , 2018 . Graph attention networks . https://arxiv.org/abs/1710.10903v1 https://arxiv.org/abs/1710.10903v1

Veličković P , Fedus W , Hamilton WL , et al. , 2019 . Deep graph infomax . https://arxiv.org/abs/1809.10341 https://arxiv.org/abs/1809.10341

Wu F , Zhang TY , Jr de Souza AH , et al. , 2019 . Simplifying graph convolutional networks . https://arxiv.org/abs/1902.07153 https://arxiv.org/abs/1902.07153

Wu ZH , Pan SR , Chen FW , et al. , 2019 . A comprehensive survey on graph neural networks . https://arxiv.org/abs/1901.00596 https://arxiv.org/abs/1901.00596

Xu K , Li CT , Tian YL , et al. , 2018 . Representation learning on graphs with jumping knowledge networks . https://arxiv.org/abs/1806.03536 https://arxiv.org/abs/1806.03536

Xu K , Hu WH , Leskovec J , et al. , 2019 . How powerful are graph neural networks? https://arxiv.org/abs/1810.00826 https://arxiv.org/abs/1810.00826

Yang ZL , Cohen W , Salakhudinov R , 2016 . Revisiting semi-supervised learning with graph embeddings . Proc 33 rd Int Conf on Machine Learning , p. 40 - 48 .

Zhou J , Cui GQ , Zhang ZY , et al. , 2018 . Graph neural networks: a review of methods and applications . https://arxiv.org/abs/1812.08434 https://arxiv.org/abs/1812.08434

Zhu XJ , Ghahramani Z , Lafferty J , 2003 . Semi-supervised learning using Gaussian fields and harmonic functions . Proc 20 th Int Conf on Machine Learning , p. 912 - 919 .

Zou DF , Hu ZN , Wang YW , et al. , 2019 . Layer-dependent importance sampling for training deep and large graph convolutional networks . Proc 33 rd Int Conf on Neural Information Processing Systems , p. 11247 - 11256 .

浏览量

102

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

工具集

关联资源

Dynamic prompting class distribution optimization for semi-supervised sound event detection

Interactive medical image segmentation with self-adaptive confidence calibration

A local density optimization method based on a graph convolutional network

Representation learning via a semi-supervised stacked distance autoencoder for image classification

Interactive image segmentation with a regression based ensemble learning paradigm