Few-Shot Node Classification Method of Graph Adaptive Prototypical Networks
GUO Ruize1, WEI Wei1,2, CUI Junbiao1, FENG Kai1,2
1. School of Computer and Information Technology, Shanxi University, Taiyuan 030006; 2. Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education, Shanxi University, Taiyuan 030006
Abstract：Few-shot node classification aims to make machines recognize and classify quickly from a small number of nodes. Existing few-shot node classification models are easily affected by the inaccurate node features extracted by encoders and the intra-class outliers of query set instances in sub-tasks. Therefore, a graph adaptive prototypical networks(GAPN) model is proposed. Firstly, the nodes are embedded into the metric space by the graph encoder. Then, prototypes are computed by fusing the global importance and the local importance as weight of support set instances, and thus more robust prototypes can be learned adaptively for query set instances. Finally, the distance between the class prototypes of the adaptive task and the query set instance is calculated to generate the classification probability. By minimizing the positive marginal feedback loss between the classification probability and the true label, network parameters are updated backward and more discriminative node features can be learned. Experimental results on common graph datasets show that GAPN model yields better node classification performance.
[1] MCAULEY J, PANDEY R, LESKOVEC J.Inferring Networks of Substitutable and Complementary Products // Proc of the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA: ACM, 2015: 785-794. [2] SINHA A, SHEN Z H, SONG Y, et al. An Overview of Microsoft Academic Service(MAS) and Applications // Proc of the 24th International Conference on World Wide Web. New York, USA: ACM, 2015: 243-246. [3] PEROZZI B, AL-RFOU R, SKIENA S.DeepWalk: Online Lear-ning of Social Representations // Proc of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA: ACM, 2014: 701-710. [4] SCARSELLI F, GORI M, TSOI A C, et al. The Graph Neural Network Model. IEEE Transactions on Neural Networks, 2009, 20(1): 61-80. [5] HAMILTON W L, YING R, LESKOVEC J.Inductive Representation Learning on Large Graphs // Proc of the 31st International Conference on Neural Information Processing Systems. Cambridge, USA: The MIT Press, 2017: 1025-1035. [6] VELIČKOVIĆ P, CUCURULL G, CASANOVA A, et al. Graph Attention Networks[J/OL].[2022-03-21]. https://arxiv.org/pdf/1710.10903.pdf. [7] ZHOU F, CAO C T, ZHANG K P, et al. Meta-GNN: On Few-Shot Node Classification in Graph Meta-Learning // Proc of the 28th ACM International Conference on Information and Knowledge Ma-nagement. New York, USA: ACM, 2019: 2357-2360. [8] KIPF T N, WELLING M.Semi-Supervised Classification with Graph Convolutional Networks[J/OL]. [2022-03-21].https://arxiv.org/pdf/1609.02907.pdf. [9] QIAO L M, SHI Y M, LI J, et al. Transductive Episodic-Wise Adaptive Metric for Few-Shot Learning // Proc of the IEEE/CVF International Conference on Computer Vision. Washington, USA: IEEE, 2019: 3602-3611. [10] YOON J, KIM T, DIA O, et al.Bayesian Model-Agnostic Meta-Learning // Proc of the 32nd International Conference on Neural Information Processing Systems. Cambridge, USA: The MIT Press, 2018: 7343-7353. [11] KOCH G, ZEMEL R, SALAKHUTDINOV R, et al. Siamese Neural Networks for One-Shot Image Recognition[C/OL].[2022-03-21]. https://www.cs.utoronto.ca/~rsalakhu/papers/oneshot1.pdf. [12] VINYALS O, BLUNDELL C, LILLICRAP T, et al.Matching Networks for One Shot Learning // Proc of the 30th International Conference on Neural Information Processing Systems. Cambridge, USA: The MIT Press, 2016: 3637-3645. [13] SNELL J, SWERSKY K, ZEMEL R S.Prototypical Networks for Few-Shot Learning // Proc of the 31st International Conference on Neural Information Processing Systems. Cambridge, USA: The MIT Press, 2017: 4077-4087. [14] SUNG F, YANG Y X, ZHANG L, et al. Learning to Compare: Relation Network for Few-Shot Learning // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2018: 1199-1208. [15] 代磊超,冯林,尚兴林,等.基于深度网络的快速少样本学习算法.模式识别与人工智能, 2021, 34(10): 941-956. (DAI L C, FENG L, SHANG X L, et al. Fast Few-Shot Learning Algorithm Based on Deep Network. Pattern Recognition and Artificial Intelligence, 2021, 34(10): 941-956.) [16] RAVI S, LAROCHELLE H.Optimization as a Model for Few-Shot Learning[C/OL]. [2022-03-21].https://openreview.net/pdf?id=rJY0-Kcll. [17] 刘鑫,周凯锐,何玉琳,等.基于度量的小样本分类方法研究综述.模式识别与人工智能, 2021, 34(10): 909-923. (LIU X, ZHOU K R, HE Y L, et al. Survey of Metric-Based Few-Shot Classification. Pattern Recognition and Artificial Intelligence, 2021, 34(10): 909-923.) [18] SUN K, LIN Z C, ZHU Z X.Multi-stage Self-Supervised Learning for Graph Convolutional Networks on Graphs with Few Labeled Nodes. Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(4): 5892-5899. [19] YAO H X, ZHANG C X, WEI Y, et al. Graph Few-Shot Learning via Knowledge Transfer. Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(4): 6656-6663. [20] WANG N, LUO M N, DING K Z, et al. Graph Few-Shot Learning with Attribute Matching // Proc of the 29th ACM International Conference on Information and Knowledge Management. New York, USA: ACM, 2020: 1545-1554. [21] DING K Z, WANG J N, LI J D, et al. Graph Prototypical Networks for Few-Shot Learning on Attributed Networks // Proc of the 29th ACM International Conference on Information and Knowledge Management. New York, USA: ACM, 2020: 295-304. [22] LIU Z M, FANG Y, LIU C H, et al. Relative and Absolute Location Embedding for Few-Shot Node Classification on Graph. Proceedings of the AAAI Conference on Artificial Intelligence, 2021, 35(5): 4267-4275. [23] GROVER A, LESKOVEC J.Node2vec: Scalable Feature Learning for Networks // Proc of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA: ACM, 2016: 855-864. [24] BRUNA J, ZAREMBA W, SZLAM A, et al. Spectral Networks. Spectral Networks and Locally Connected Networks on Graphs[J/OL]. [2022-03-21]. https://arxiv.org/pdf/1312.6203.pdf. [25] GARCIA V, BRUNA J.Few-Shot Learning with Graph Neural Net-works[J/OL]. [2022-03-21].https://arxiv.org/pdf/1711.04043.pdf. [26] YANG L, LI L L, ZHANG Z L, et al. DPGN: Distribution Propagation Graph Network for Few-Shot Learning // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2020: 13387-13396.
2022, Vol. 35 
