Few-shot node classification via local adaptive discriminant structure learning

doi:10.1007/s11704-022-1259-6

Front. Comput. Sci.

2023, Vol. 17

Issue (2) : 172316 https://doi.org/10.1007/s11704-022-1259-6

RESEARCH ARTICLE

Few-shot node classification via local adaptive discriminant structure learning

Zhe XUE, Junping DU(

), Xin XU, Xiangbin LIU, Junfu WANG, Feifei KOU

Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia, School of Computer Science, Beijing University of Posts and Telecommunications, Beijing 100876, China

Download: PDF(4253 KB) HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

Abstract

Node classification has a wide range of application scenarios such as citation analysis and social network analysis. In many real-world attributed networks, a large portion of classes only contain limited labeled nodes. Most of the existing node classification methods cannot be used for few-shot node classification. To train the model effectively and improve the robustness and reliability of the model with scarce labeled samples, in this paper, we propose a local adaptive discriminant structure learning (LADSL) method for few-shot node classification. LADSL aims to properly represent the nodes in the attributed graphs and learn a metric space with a strong discriminating power by reducing the intra-class variations and enlarging inter-class differences. Extensive experiments conducted on various attributed networks datasets demonstrate that LADSL is superior to the other methods on few-shot node classification task.

Keywords few-shot learning node classification graph neural network adaptive structure learning attention strategy

Corresponding Author(s): Junping DU

Just Accepted Date: 16 February 2022 Issue Date: 02 August 2022

Cite this article:

Zhe XUE,Junping DU,Xin XU, et al. Few-shot node classification via local adaptive discriminant structure learning[J]. Front. Comput. Sci., 2023, 17(2): 172316.

URL:

https://academic.hep.com.cn/fcs/EN/10.1007/s11704-022-1259-6
https://academic.hep.com.cn/fcs/EN/Y2023/V17/I2/172316

Fig.1 The framework of the proposed local adaptive discriminant structure learning (LADSL) method

Tab.1 Statistics of datasets

Tab.2 Averaged few-shot node classification results on Amazon-Clothing dataset

Tab.3 Averaged few-shot node classification results on DBLP dataset

Tab.4 Averaged few-shot node classification results on Amazon-Electronics dataset

Fig.2 t-SNE visualization of node features on Amazon-Clothing and DLBP datasets. (a) Original feature on Amazon-Clothing; (b) node feature learned by LADSL on Amazon-Clothing; (c) original feature on DBLP; (d) node feature learned by LADSL on DBLP

Fig.3 Ablation study results on Amazon-Clothing dataset. (a) 5-way-3-shot; (b) 5-way-5-shot; (c) 10-way-3-shot; (d) 10-way-5-shot

Fig.4 Ablation study results on DBLP dataset. (a) 5-way-3-shot; (b) 5-way-5-shot; (c) 10-way-3-shot; (d) 10-way-5-shot

Fig.5 Parameter sensitivity analysis on each dataset. (a) Amazon-Clothing; (b) Amazon-Electronics; (c) DBLP

1	J, Tang J, Zhang L, Yao J, Li L, Zhang Z Su. ArnetMiner: extraction and mining of academic social networks. In: Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2008, 990– 998
2	K, Ding J, Li N, Agarwal H Liu. Inductive anomaly detection on attributed networks. In: Proceedings of the 29th International Joint Conference on Artificial Intelligence, IJCAI 2020. 2020, 1288– 1294
3	L, Liao X, He H, Zhang T S Chua . Attributed social network embedding. IEEE Transactions on Knowledge and Data Engineering, 2018, 30( 12): 2257– 2270
4	S, Tabassum F S F, Pereira S, Fernandes J Gama . Social network analysis: an overview. WIREs Data Mining and Knowledge Discovery, 2018, 8( 5): e1256
5	L, Yao C, Mao Y Luo. Graph convolutional networks for text classification. In: Proceedings of the 33rd AAAI Conference on Artificial Intelligence. 2019, 905
6	S, Abu-El-Haija A, Kapoor B, Perozzi J Lee. N-GCN: multi-scale graph convolution for semi-supervised node classification. In: Proceedings of the 35th Uncertainty in Artificial Intelligence Conference. 2020, 841– 851
7	S, Gidaris N Komodakis. Generating classification weights with GNN denoising autoencoders for few-shot learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019, 21– 30
8	S, Bhagat G, Cormode S Muthukrishnan. Node classification in social networks. In: Aggarwal C C, ed. Social Network Data Analytics. Boston: Springer, 2011, 115− 148
9	Z, Zhou Y, Gu G Yu . Adversarial network embedding using structural similarity. Frontiers of Computer Science, 2021, 15( 1): 151603
10	Z, Xue J, Du C, Zheng J, Song W, Ren M Liang. Clustering-induced adaptive structure enhancing network for incomplete multi-view data. In: Proceedings of the 30th International Joint Conference on Artificial Intelligence, IJCAI-21. 2021, 3235– 3241
11	J, Snell K, Swersky R S Zemel. Prototypical networks for few-shot learning. In: Proceedings of the 31st Conference on Neural Information Processing Systems. 2017, 4077– 4087
12	W, Hu J, Gao B, Li O, Wu J, Du S Maybank . Anomaly detection using local kernel density estimation and context-based regression. IEEE Transactions on Knowledge and Data Engineering, 2020, 32( 2): 218– 233
13	R, Zhang T, Che Z, Ghahramani Y, Bengio Y Song. MetaGAN: an adversarial approach to few-shot learning. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems. 2018, 2371– 2380
14	G, Koch R, Zemel R Salakhutdinov. Siamese neural networks for one-shot image recognition. In: Proceedings of the 32nd International Conference on Machine Learning. 2015
15	L, Xu J, Du Q Li . Image fusion based on nonsubsampled contourlet transform and saliency-motivated pulse coupled neural networks. Mathematical Problems in Engineering, 2013, 2013: 135182
16	C, Finn P, Abbeel S Levine. Model-agnostic meta-learning for fast adaptation of deep networks. In: Proceedings of the 34th International Conference on Machine Learning. 2017, 1126– 1135
17	F, Sung Y, Yang L, Zhang T, Xiang P H S, Torr T M Hospedales. Learning to compare: relation network for few-shot learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2018, 1199– 1208
18	Z, Xue J, Du D, Du W, Ren S Lyu. Deep correlated predictive subspace learning for incomplete multi-view semi-supervised classification. In: Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI). 2019, 4026– 4032
19	X, Yang X, Nan B Song . D2N4: a discriminative deep nearest neighbor neural network for few-shot space target recognition. IEEE Transactions on Geoscience and Remote Sensing, 2020, 58( 5): 3667– 3676
20	Y, Fang W, Deng J, Du J Hu . Identity-aware CycleGAN for face photo-sketch synthesis and recognition. Pattern Recognition, 2020, 102: 107249
21	J, Kim T, Kim S, Kim C D Yoo. Edge-labeling graph neural network for few-shot learning. In: Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2019, 11– 20
22	Y, Liu J, Lee M, Park S, Kim E, Yang S J, Hwang Y Yang. Learning to propagate labels: transductive propagation network for few-shot learning. In: Proceedings of the 7th International Conference on Learning Representations. 2019
23	F, Scarselli M, Gori A C, Tsoi M, Hagenbuchner G Monfardini . The graph neural network model. IEEE Transactions on Neural Networks, 2009, 20( 1): 61– 80
24	J, Bruna W, Zaremba A, Szlam Y LeCun. Spectral networks and locally connected networks on graphs. In: Proceedings of the 2nd International Conference on Learning Representations. 2014
25	M, Defferrard X, Bresson P Vandergheynst. Convolutional neural networks on graphs with fast localized spectral filtering. In: Proceedings of the 30th International Conference on Neural Information Processing Systems. 2016, 3844– 3852
26	T N, Kipf M Welling. Semi-supervised classification with graph convolutional networks. In: Proceedings of the 5th International Conference on Learning Representations. 2017
27	K X, Yu Z J, Qiao W L, Song S Bi . DNA nanotechnology for multimodal synergistic theranostics. Journal of Analysis and Testing, 2021, 5( 2): 112– 129
28	W L, Hamilton R, Ying J Leskovec. Inductive representation learning on large graphs. In: Proceedings of the 31st International Conference on Neural Information Processing Systems. 2017, 1025– 1035
29	P, Veličković G, Cucurull A, Casanova A, Romero P, Liò Y Bengio. Graph attention networks. In: Proceedings of the 6th International Conference on Learning Representations. 2018, 1– 12
30	K, Xu W, Hu J, Leskovec S Jegelka. How powerful are graph neural networks? In: Proceedings of the 7th International Conference on Learning Representations (ICLR). 2019
31	N, Mishra M, Rohaninejad X, Chen P Abbeel. A simple neural attentive meta-learner. In: Proceedings of the 6th International Conference on Learning Representations. 2018
32	Z, Xue J, Du D, Du S Lyu . Deep low-rank subspace ensemble for multi-view clustering. Information Sciences, 2019, 482: 210– 227
33	S, Ravi H Larochelle. Optimization as a model for few-shot learning. In: Proceedings of the 5th International Conference on Learning Representations. 2017
34	O, Vinyals C, Blundell T, Lillicrap K, Kavukcuoglu D Wierstra. Matching networks for one shot learning. In: Proceedings of the 30th International Conference on Neural Information Processing Systems. 2016, 3637– 3645
35	M, Ren E, Triantafillou S, Ravi J, Snell K, Swersky J B, Tenenbaum H, Larochelle R S Zemel. Meta-learning for semi-supervised few-shot classification. In: Proceedings of the 6th International Conference on Learning Representations. 2018
36	L, Liu T, Zhou G, Long J, Jiang C Zhang. Learning to propagate for graph meta-learning. In: Proceedings of the 33rd Conference on Neural Information Processing Systems (NeurIPS). 2019, 1037– 1048
37	T H, Fereja F, Du C, Wang D, Snizhko Y, Guan G Xu . Electrochemiluminescence imaging techniques for analysis and visualizing. Journal of Analysis and Testing, 2020, 4( 2): 76– 91
38	F, Zhou C, Cao K, Zhang G, Trajcevski T, Zhong J Geng. Meta-GNN: on few-shot node classification in graph meta-learning. In: Proceedings of the 28th ACM International Conference on Information and Knowledge Management. 2019, 2357– 2360
39	K, Ding J, Wang J, Li K, Shu C, Liu H Liu. Graph prototypical networks for few-shot learning on attributed networks. In: Proceedings of the 29th ACM International Conference on Information & Knowledge Management. 2020, 295– 304
40	Y, Wen K, Zhang Z, Li Y Qiao. A discriminative feature learning approach for deep face recognition. In: Proceedings of the 14th European Conference on Computer Vision. 2016, 499– 515
41	J, McAuley R, Pandey J Leskovec. Inferring networks of substitutable and complementary products. In: Proceedings of the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2015, 785– 794
42	B, Perozzi R, Al-Rfou S Skiena. DeepWalk: online learning of social representations. In: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2014, 701– 710
43	A, Grover J Leskovec. node2vec: scalable feature learning for networks. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2016, 855– 864
44	F, Wu T, Zhang Souza A H Jr, de C, Fifty T, Yu K Q Weinberger. Simplifying graph convolutional networks. In: Proceedings of the 36th International Conference on Machine Learning. 2019, 6861– 6871
45	MindSpore. mindspore website, 2021
46	der Maaten L, van G Hinton . Visualizing data using t-SNE. Journal of Machine Learning Research, 2008, 9( 86): 2579– 2605

[1]

FCS-21259-OF-ZX_suppl_1

Download

[1]	Miao ZHANG, Tingting HE, Ming DONG. Meta-path reasoning of knowledge graph for commonsense question answering[J]. Front. Comput. Sci., 2024, 18(1): 181303-.
[2]	Yongquan LIANG, Qiuyu SONG, Zhongying ZHAO, Hui ZHOU, Maoguo GONG. BA-GNN: Behavior-aware graph neural network for session-based recommendation[J]. Front. Comput. Sci., 2023, 17(6): 176613-.
[3]	Jinwei LUO, Mingkai HE, Weike PAN, Zhong MING. BGNN: Behavior-aware graph neural network for heterogeneous session-based recommendation[J]. Front. Comput. Sci., 2023, 17(5): 175336-.
[4]	Qiming FU, Zhechao WANG, Nengwei FANG, Bin XING, Xiao ZHANG, Jianping CHEN. MAML²: meta reinforcement learning via meta-learning for task categories[J]. Front. Comput. Sci., 2023, 17(4): 174325-.
[5]	Yuan GAO, Xiang WANG, Xiangnan HE, Huamin FENG, Yongdong ZHANG. Rumor detection with self-supervised learning on texts and social graph[J]. Front. Comput. Sci., 2023, 17(4): 174611-.
[6]	Shuang LIU, Fan ZHANG, Baiyang ZHAO, Renjie GUO, Tao CHEN, Meishan ZHANG. APPCorp: a corpus for Android privacy policy document structure analysis[J]. Front. Comput. Sci., 2023, 17(3): 173320-.
[7]	Zhong JI, Jingwei NI, Xiyao LIU, Yanwei PANG. Teachers cooperation: team-knowledge distillation for multiple cross-domain few-shot learning[J]. Front. Comput. Sci., 2023, 17(2): 172312-.
[8]	Wei GAO, Mingwen SHAO, Jun SHU, Xinkai ZHUANG. Meta-BN Net for few-shot learning[J]. Front. Comput. Sci., 2023, 17(1): 171302-.
[9]	Pinzhuo TIAN, Yang GAO. Improving meta-learning model via meta-contrastive loss[J]. Front. Comput. Sci., 2022, 16(5): 165331-.

Viewed

Full text

Abstract

Cited

Shared

Discussed