Skip to main content
Disciplines
Automotive Business IT + Informatics Construction + Real Estate Electrical Engineering + Electronics Energy + Sustainability Insurance + Risk Finance + Banking Management + Leadership Marketing + Sales Mechanical Engineering + Materials
Events
DE
EN
Books
Journals
Topic Page
Marketing
Start single access now
Access for companies
EXTENDED SEARCH
Log in
Top
International Journal of Machine Learning and Cybernetics
Published in: International Journal of Machine Learning and Cybernetics 5/2024

14-11-2023 | Original Article

SSGCN: a sampling sequential guided graph convolutional network

Authors: Xiaoxiao Wang, Xibei Yang, Pingxin Wang, Hualong Yu, Taihua Xu

Published in: International Journal of Machine Learning and Cybernetics | Issue 5/2024

Log in

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

Graph convolutional networks(GCNs) have become one of the important technologies for solving graph structured data problems. GCNs utilize convolutional networks to learn node and spatial features in the graph, and fully fuse them for node classification tasks. Consequently, for most GCNs, “graph convolution” operation over the set of nodes is the key. Nevertheless, such an operation is frequently embedded into a fixed graph without considering the dynamic variation of the set of nodes. Immediately, the incremental learning mechanism can be considered. From this viewpoint, a Sampling Sequential Guided Graph Convolutional Network (SSGCN) is developed. Firstly, through random sampling over the set of nodes, multiple minibatch graphs can be obtained. Secondly, by the proposed sequential guidance, the weight matrices can be updated incrementally by using “graph convolution” over minibatch graphs one by one. That is, the trained weight matrix of the previous minibatch graph is saved, which in turn is used as an input for training the next minibatch graph. Finally, the prediction results from all minibatch graph learners are integrated. We conducted experiments based on the standard variance of different \(\tau\) number of losses, and over three common citation network datasets (Cora, Citeseer and Pubmed) to evaluate the performance of SSGCN in node classification tasks. The experimental results show that, in comparison study and ablation study,in terms of both efficiency and effectiveness, the performance of SSGCN is superior to most state-of-the-art methods. In addition, SSGCN shows good convergence in visualization.
previous article Hessian unsupervised extreme learning machine
next article Self-supervised learning-leveraged boosting ultrasound image segmentation via mask reconstruction

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

inform now
Show more products
Literature
1.
Abu-El-Haija S, Perozzi B, Kapoor A, Alipourfard N, Lerman K, Harutyunyan H, Steeg GV, Galstyan A (2019) MixHop: higher-order graph convolutional architectures via sparsified neighborhood mixing. In: International conference on machine learning, pp 21–29
2.
Ahmad F, Farooq A, Ghani MU (2021) Deep ensemble model for classification of novel coronavirus in chest X-ray images. Comput Intell Neurosci 8890226:1–17
3.
Ahmad F, Khan MUG, Javed K (2021) Deep learning model for distinguishing novel coronavirus from other chest related infections in X-ray images. Comput Biol Med 134:104401
4.
Ahmad F, Khan MUG, Tahir A, Tipu MY, Rabbani M, Shabbir MZ (2023) Two phase feature-ranking for new soil dataset for Coxiella Burnetii persistence and classification using machine learning models. Sci Rep 13(1):29
5.
Bouchachia A, Nedjah N (2011) Adaptive incremental learning in neural networks. Neurocomputing 74(11):1783–1784
6.
Bruna JW, Zaremba A, Szlam Y (2014) LeCun, spectral networks and locally connected networks on graphs. In: International conference on learning representations
7.
Cao SS, Lu W, Xu QK (2015) GraRep: learning graph representations with global structural information. In: Knowledge discovery and data mining, pp 891–900
8.
Chen JY, Gong ZG, Wang W, Wang C, Xu ZH, Lv JM, Li XL, Wu KS, Liu WW (2022) Adversarial caching training: unsupervised inductive network representation learning on large-scale graphs. IEEE Trans Neural Netw Learn Syst 33(12):7079–7090
9.
Chen Z, Liu KY, Yang XB, Fujita H (2022) Random sampling accelerator for attribute reduction. Int J Approx Reason 140:75–91MathSciNet
10.
Chen J, Ma TF, Xiao C (2018) FastGCN: fast learning with graph convolutional networks via importance sampling. In: International conference on learning representations
11.
Chen Y, Yang XB, Li JH, Wang PX, Qian YH (2022) Fusing attribute reduction accelerators. Inf Sci 587:354–370
12.
Chiang WL, Liu XQ, Si Si, Li Y, Bengio S, Hsieh CJ (2019) Cluster-GCN: an efficient algorithm for training deep and large graph convolutional networks. In: Knowledge discovery and data mining, pp 257–266
13.
Deepa I, Archana S (2022) Multi-module convolutional neural network based optimal face recognition with minibatch optimization. Int J Image Graph Signal Process (IJIGSP) 14(3):32–46
14.
Fan WQ, Ma Y, Li Q, He Y, Zhao E, Tang JL, Yin DW (2019) Graph neural networks for social recommendation. In: The international conference of world wide web, pp 417–426
15.
Flexa C, Gomes WC, Moreira I, Alves R, Sales C (2021) Polygonal coordinate system: visualizing high-dimensional data using geometric DR, and a deterministic version of t-SNE. Expert Syst Appl 175:114741
16.
Fu SC, Liu WF, Zhang K, Zhou YC, Tao DP (2021) Semi-supervised classification by graph p-Laplacian convolutional networks. Inf Sci 560:92–106MathSciNet
17.
Gao HY, Ji SW (2022) Graph U-Nets. IEEE Trans Pattern Anal Mach Intell 44(9):4948–4960
18.
Gao MR, Ruan NJ, Shi JP, Zhou WL (2022) Deep neural network for 3D shape classification based on mesh feature. Sensors 22(18):7040
19.
Hamilton WL, Ying ZT, Leskovec J (2017) Inductive representation learning on large graphs. In: Conference and workshop on neural information processing systems, pp 1024–1034
20.
He LC, Bai L, Yang X, Du HY, Liang JY (2023) High-order graph attention network. Inf Sci 630:222–234
21.
He HB, Chen S, Li K, Xu X (2011) Incremental learning from stream data. IEEE Trans Neural Netw 22(12):1901–1914
22.
Hell F, Taha Y, Hinz G, Heibei S, Müller H, Knoll A (2020) Graph convolutional neural network for a pharmacy cross-selling recommender system. Information 11(11):525
23.
Hou X, Luo JT, Li JZ, Wang LG, Yang HB (2022) A novel knowledge base question answering method based on graph convolutional network and optimized search space. Electronics 11(23):3897
24.
Huang WB, Zhang T, Rong Y, Huang JZ (2018) Adaptive sampling towards fast graph representation learning. In: Conference on neural information processing systems, pp 4563–4572
25.
Kim D, Kim YJ, Jeong YS (2022) Graph convolutional networks with POS gate for aspect-based sentiment analysis. Appl Sci 12(19):10134
26.
Kingma DP, Ba J (2015) Adam: a method for stochastic optimization. In: International conference on learning representations
27.
Kipf TN, Welling M (2017) Semi-supervised classification with graph convolutional networks. In: International conference on learning representations
28.
Kwon J (2021) Graph visual tracking using conditional uncertainty minimization and minibatch Monte Carlo inference. Inf Sci 574:363–376MathSciNet
29.
Lan ZX, He Q, Yang L (2022) Dual-channel interactive graph convolutional networks for aspect-level sentiment analysis. Mathematics 10(18):3317
30.
Li GH, Fang T, Zhang YJ, Liang C, Xiao Q, Luo JW (2022) Predicting MiRNA-disease associations based on graph attention network with multi-source information. BMC Bioinf 23(1):244
31.
Liu KY, Li TR, Yang XB, Yang X, Liu D (2022) Neighborhood rough set based ensemble feature selection with cross-class sample granulation. Appl Soft Comput 131:109747
32.
Liu KY, Li TR, Yang XB, Yang X, Liu D, Zhang PF, Wang J (2022) Granular Cabin: an efficient solution to neighborhood learning in big data. Inf Sci 583:189–201
33.
Liu KY, Yang XB, Yu HL, Mi JS, Wang PX, Chen XJ (2019) Rough set based semi-supervised feature selection via ensemble selector. Knowl-Based Syst 165:282–296
34.
Liu Y, Yao X, Higuchi T (2000) Evolutionary ensembles with negative correlation learning. IEEE Trans Evol Comput 4(4):380–387
35.
Li KJ, Ye WJ (2022) Semi-supervised node classification via graph learning convolutional neural network. Appl Intell 52(11):12724–12736
36.
Lorenzo PD, Banelli P, Isufi E, Barbarossa S, Leus G (2018) Adaptive graph signal processing: algorithms and optimal sampling strategies. IEEE Trans Signal Process 66(13):3584–3598MathSciNet
37.
Maaten LVD, Hinton G (2008) Visualizing data using t-SNE. J Mach Learn Res 9(2605):2579–2605
38.
Najafi B, Parsaeefard S, Leon-Garcia A (2022) Missing data estimation in temporal multilayer position-aware graph neural network (TMP-GNN). Mach Learn Knowl Extract 4(2):397–417
39.
Nan AMM (2022) Florea, fast temporal graph convolutional model for skeleton-based action recognition. Sensors 22(19):7117
40.
Necoara I, Nedic A (2021) Minibatch stochastic subgradient-based projection algorithms for feasibility problems with convex inequalities. Comput Optim Appl 80(1):121–152MathSciNet
41.
Nt H, Maehara T (2021) Revisiting graph neural networks: all we have is low-pass filters. In: 25th International conference on pattern recognition, pp 8376–8383
42.
Peng YB, Liu CX, Wu YT, Liu SX, Wang K (2022) Graph convolutional networks-based robustness optimization for scale-free internet of things. Intell Data Anal 26(6):1683–1701
43.
Peng XY, Li L, Wang FY (2020) Accelerating minibatch stochastic gradient descent using typicality sampling. IEEE Trans Neural Netw Learn Syst 31(11):4649–4659MathSciNet
44.
Tang J, Qu M, Wang MZ, Zhang M, Yan J, Mei QZ (2015) LINE: large-scale information network embedding. In: The international conference of world wide web, pp 1067–1077
45.
Tang BH, Wang JF, Qiu HR, Yu J, Yu ZK, Liu SJ (2022) Attack behavior extraction based on heterogeneous cyberthreat intelligence and graph convolutional networks. Comput Mater Continua 74(1):235–252
46.
Tao XY, Chang XY, Hong XP, Wei X, Gong YH (2020) Topology-preserving class-incremental learning. In: European conference on computer vision, pp 254–270
47.
Tao XY, Hong XP, Chang XY, Dong SL, Wei X, Gong YH (2020) Few-shot class-incremental learning. In: IEEE conference on computer vision and pattern recognition, pp 12180–12189
48.
Velickovic P, Cucurull G, Casanova A, Romero A, Liò Y, Bengio P (2018) Graph attention networks. In: International conference on learning representations
49.
Wang DX, Cui P, Zhu WW (2016) Structural deep network embedding. In: Knowledge discovery and data mining, pp 1225-1234
50.
Wang JJ, Chen QK, Gong HL (2020) Stmag: a spatial-temporal mixed attention graph-based convolution model for multi-data flow safety prediction. Inf Sci 525:16–36
51.
Wang X, Cui P, Wang J, Pei J, Zhu WW, Yang SQ (2017) Community preserving network embedding, association for the advancement of artificial intelligence, pp 203–209
52.
Wang J, Liang JQ, Cui JB, Liang JY (2021) Semi-supervised learning with mixed-order graph convolutional networks. Inf Sci 573:171–181MathSciNet
53.
Wang X, Zhu MQ, Bo DY, Cui P, Shi C, Pei J (2020) AM-GCN: adaptive multi-channel graph convolutional networks. In: Knowledge discovery and data mining, pp 1243–1253
54.
Wu J, He JR, Xu JJ (2019) Demo-net: degree-specific graph neural networks for node and graph classification. In: Knowledge discovery and data mining, pp 406–415
55.
Wu BH, Li LL (2022) Solving maximum weighted matching on large graphs with deep reinforcement learning. Inf Sci 614:400–415
56.
Wu F, Zhang T Yi, Souza AHD, Fifty C, Yu T, Weinberger KQ (2019) Simplifying graph convolutional networks. In: International conference on machine learning, pp 6861–6871
57.
Xu LC, Wei XK, Cao JN, Yu PS (2017) Embedding identity and interest for social networks. In: The international conference of world wide web, pp 859–860
58.
Xu H, Liu SX, Wang W, Deng L (2022) RAG-TCGCN: aspect sentiment analysis based on residual attention gating and three-channel graph convolutional networks. Appl Sci 12(23):12108
59.
Xu GT, Liu PY, Zhu ZF, Liu J, Xu FY (2021) Attention-enhanced graph convolutional networks for aspect-based sentiment classification with multi-head attention. Appl Sci 11(8):3640
60.
Yang JJ, Dai A, Xue Y, Zeng BQ, Liu XJ (2022) Syntactically enhanced dependency-POS weighted graph convolutional network for aspect-based sentiment analysis. Mathematics 10(18):3353
61.
Yang X, Liu D, Yang XB, Liu KY, Li TR (2021) Incremental fuzzy probability decision-theoretic approaches to dynamic three-way approximations. Inf Sci 550:71–90MathSciNet
62.
Yang XB, Qi Y, Yu HL, Song XN, Yang JY (2014) Updating multigranulation rough approximations with increasing of granular structures. Knowl Based Syst 64:59–69
63.
Yang XB, Yao YY (2018) Ensemble selector for attribute reduction. Appl Soft Comput 70:1–11
64.
Yao L, Mao CS, Luo Y (2019) Graph convolutional networks for text classification. In: Proceedings of the AAAI conference on artificial intelligence, pp 7370–7377
65.
You JX, Ying R, Leskovec J (2019) Position-aware graph neural networks. In: International conference on machine learning, pp 7134–7143
66.
Zeng ZY, Xu YY, Xie Z, Wan J, Wu WC, Dai WX (2022) RG-GCN: a random graph based on graph convolution network for point cloud semantic segmentation. Remote Sens 14(16):4055
67.
Zeng H, Zhou H, Srivastava A, Kannan R, Prasanna VK (2019) Accurate, efficient and scalable graph embedding. In: IEEE international parallel and distributed processing symposium, pp 462–471
68.
Zhai R, Zhang LB, Wang YQ, Song YL, Yu JY (2023) A multi-channel attention graph convolutional neural network for node classification. J Supercomput 79(4):3561–3579
69.
Zhang MH, Cui ZC, Neumann M, Chen YX (2018) An end-to-end deep learning architecture for graph classification. In: Association for the advancement of artificial intelligence, pp 4438–4445
70.
Zhang JT, Lan H, Yang XD, Zhang SC, Song W, Peng ZY (2022) Weakly supervised setting for learning concept prerequisite relations using multi-head attention variational graph auto-encoders. Knowl Based Syst 247:108689
71.
Zhang ZX, Ma ZH, Cai SH, Chen JH, Xue Y (2022) Knowledge-enhanced dual-channel GCN for aspect-based sentiment analysis. Mathematics 10(22):4273
72.
Zhang C, Song N, Lin GS, Zheng Y, Pan P, Xu YH (2021) Few-shot incremental learning with continually evolved classifiers. In: IEEE conference on computer vision and pattern recognition, pp 12455–12464
73.
Zhang S, Tong HH, Xu JJ, Maciejewski R (2019) Graph convolutional networks: a comprehensive review. Comput Soc Netw 6(1):11
74.
Zhu XL, Liu GD, Zhao L, Rong WT, Sun JY, Liu R (1917) Emotion classification from multi-band electroencephalogram data using dynamic simplifying graph convolutional network and channel style recalibration module. Sensors 23(4):2023
Metadata
Title
SSGCN: a sampling sequential guided graph convolutional network
Authors
Xiaoxiao Wang
Xibei Yang
Pingxin Wang
Hualong Yu
Taihua Xu
Publication date
14-11-2023
Publisher
Springer Berlin Heidelberg
Published in
International Journal of Machine Learning and Cybernetics / Issue 5/2024
Print ISSN: 1868-8071
Electronic ISSN: 1868-808X
DOI
https://doi.org/10.1007/s13042-023-02013-2

Other articles of this Issue 5/2024

International Journal of Machine Learning and Cybernetics 5/2024 Go to the issue

Original Article

Fuzzy large margin distribution machine for classification

Original Article

Filtering level-set model based on saliency and gradient information for sonar image segmentation

Original Article

Hessian unsupervised extreme learning machine

Original Article

A new robust contrastive learning for unsupervised person re-identification

Original Article

Feature selection for label distribution learning under feature weight view

Original Article

Adaptive intuitionistic fuzzy neighborhood classifier