A journal of IEEE and CAA , publishes high-quality papers in English on original theoretical/experimental research and development in all areas of automation
Volume 9 Issue 2
Feb.  2022

IEEE/CAA Journal of Automatica Sinica

  • JCR Impact Factor: 11.8, Top 4% (SCI Q1)
    CiteScore: 17.6, Top 3% (Q1)
    Google Scholar h5-index: 77, TOP 5
Turn off MathJax
Article Contents
X. Liu, M. Y. Yan, L. Deng, G. Q. Li, X. C. Ye, and D. R. Fan, “Sampling methods for efficient training of graph convolutional networks: A survey,” IEEE/CAA J. Autom. Sinica, vol. 9, no. 2, pp. 205–234, Feb. 2022. doi: 10.1109/JAS.2021.1004311
Citation: X. Liu, M. Y. Yan, L. Deng, G. Q. Li, X. C. Ye, and D. R. Fan, “Sampling methods for efficient training of graph convolutional networks: A survey,” IEEE/CAA J. Autom. Sinica, vol. 9, no. 2, pp. 205–234, Feb. 2022. doi: 10.1109/JAS.2021.1004311

Sampling Methods for Efficient Training of Graph Convolutional Networks: A Survey

doi: 10.1109/JAS.2021.1004311
Funds:  This work was partially supported by the National Natural Science Foundation of China (61732018, 61872335, 61802367, 61876215), the Strategic Priority Research Program of Chinese Academy of Sciences (XDC05000000), Beijing Academy of Artificial Intelligence (BAAI), the Open Project Program of the State Key Laboratory of Mathematical Engineering and Advanced Computing (2019A07), the Open Project of Zhejiang Laboratory, and a grant from the Institute for Guo Qiang, Tsinghua University
More Information
  • Graph convolutional networks (GCNs) have received significant attention from various research fields due to the excellent performance in learning graph representations. Although GCN performs well compared with other methods, it still faces challenges. Training a GCN model for large-scale graphs in a conventional way requires high computation and storage costs. Therefore, motivated by an urgent need in terms of efficiency and scalability in training GCN, sampling methods have been proposed and achieved a significant effect. In this paper, we categorize sampling methods based on the sampling mechanisms and provide a comprehensive survey of sampling methods for efficient training of GCN. To highlight the characteristics and differences of sampling methods, we present a detailed comparison within each category and further give an overall comparative analysis for the sampling methods in all categories. Finally, we discuss some challenges and future research directions of the sampling methods.

     

  • loading
  • [1]
    A. M. Fout, “Protein interface prediction using graph convolutional networks,” Ph.D. dissertation, Colorado State University, Fort Collins, Colorado, 2017.
    [2]
    S. Guo, Y. Lin, N. Feng, C. Song, and H. Wan, “Attention based spatial-temporal graph convolutional networks for traffic flow forecasting,” in Proc. AAAI Conf. Artificial Intelligence, 2019, vol. 33, no. 01, pp. 922–929.
    [3]
    Z. Cui, K. Henrickson, R. Ke, and Y. Wang, “Traffic graph convolutional recurrent neural network: A deep learning framework for network-scale traffic learning and forecasting,” IEEE Trans. Intelligent Transportation Systems, vol. 21, no. 11, pp. 4883–4894, 2019.
    [4]
    Z. Wang, Q. Lv, X. Lan, and Y. Zhang, “Cross-lingual knowledge graph alignment via graph convolutional networks,” in Proc. Conf. Empirical Methods in Natural Language Processing, 2018, pp. 349–357.
    [5]
    C. Shang, Y. Tang, J. Huang, J. Bi, X. He, and B. Zhou, “End-to-end structure-aware convolutional networks for knowledge base completion,” in Proc. AAAI Conf. Artificial Intelligence, 2019, vol. 33, no. 01, pp. 3060–3067.
    [6]
    J. Zhou, G. Cui, S. Hu, Z. Zhang, C. Yang, Z. Liu, L. Wang, C. Li, and M. Sun, “Graph neural networks: A review of methods and applications,” AI Open, vol. 1, pp. 57–81, 2020. doi: 10.1016/j.aiopen.2021.01.001
    [7]
    F. Scarselli, M. Gori, A. C. Tsoi, M. Hagenbuchner, and G. Monfardini, “The graph neural network model,” IEEE Trans. Neural Networks, vol. 20, no. 1, pp. 61–80, 2008.
    [8]
    P. W. Battaglia, J. B. Hamrick, V. Bapst, A. SanchezGonzalez, V. Zambaldi, M. Malinowski, A. Tacchetti, D. Raposo, A. Santoro, R. Faulkner, and C. Gulcehre, “Relational inductive biases, deep learning, and graph networks,” arXiv preprint arXiv: 1806.01261, 2018.
    [9]
    H. Akita, K. Nakago, T. Komatsu, Y. Sugawara, S.-i. Maeda, Y. Baba, and H. Kashima, “Bayesgrad: Explaining predictions of graph convolutional networks,” in Proc. Int. Conf. Neural Information Processing, Springer, 2018, pp. Proc. 81–92.
    [10]
    R. Ying, D. Bourgeois, J. You, M. Zitnik, and J. Leskovec, “Gnnexplainer: Generating explanations for graph neural networks,” in Proc. Advances in Neural Information Processing Systems, 2019, pp. 9244–9255.
    [11]
    F. Baldassarre and H. Azizpour, “Explainability techniques for graph convolutional networks,” arXiv preprint arXiv: 1905.13686, 2019
    [12]
    P. E. Pope, S. Kolouri, M. Rostami, C. E. Martin, and H. Hoffmann, “Explainability methods for graph convolutional neural networks,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition, 2019, pp. 10 772–10 781.
    [13]
    K. Xu, J. Li, M. Zhang, S. S. Du, K.-i. Kawarabayashi, and S. Jegelka, “What can neural networks reason about?” arXiv preprint arXiv: 1905.13211, 2019.
    [14]
    H. Yuan, H. Yu, S. Gui, and S. Ji, “Explainability in graph neural networks: A taxonomic survey,” arXiv preprint arXiv: 2012.15445, 2020.
    [15]
    Y. Li, D. Tarlow, M. Brockschmidt, and R. Zemel, “Gated graph sequence neural networks,” arXiv preprint arXiv: 1511.05493, 2015.
    [16]
    M. Henaff, J. Bruna, and Y. LeCun, “Deep convolutional networks on graph-structured data,” arXiv preprint arXiv: 1506.05163, 2015.
    [17]
    J. Atwood and D. Towsley, “Diffusion-convolutional neural networks,” in Advances Neural Information Processing Systems, 2016, pp. 1993–2001.
    [18]
    P. Veličković, G. Cucurull, A. Casanova, A. Romero, P. Liò, and Y. Bengio, “Graph Attention Networks,” in Proc Int. Conf. Learning Representations, 2018, pp. 1–12. [Online]. Available: https://openreview.net/forum?id=rJXMpikCZ
    [19]
    M. Defferrard, X. Bresson, and P. Vandergheynst, “Convolutional neural networks on graphs with fast localized spectral filtering,” in Proc. Advances in Neural Information Processing Systems, 2016, vol. 29, pp. 3844–3852.
    [20]
    M. Niepert, M. Ahmed, and K. Kutzkov, “Learning convolutional neural networks for graphs,” in Proc. Int. Conf. Machine Learning, PMLR, 2016, pp. 2014–2023.
    [21]
    T. N. Kipf and M. Welling, “Semi-supervised classification with graph convolutional networks,” in Proc. Int. Conf. Learning Representations (ICLR), 2017, pp. 1–14.
    [22]
    F. Monti, D. Boscaini, J. Masci, E. Rodola, J. Svoboda, and M. M. Bronstein, “Geometric deep learning on graphs and manifolds using mixture model cnns,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2017, pp. 5115–5124.
    [23]
    J. Bruna, W. Zaremba, A. Szlam, and Y. LeCun, “Spectral networks and locally connected networks on graphs,” arXiv preprint arXiv: 1312.6203, 2013.
    [24]
    F. Wu, A. Souza, T. Zhang, C. Fifty, T. Yu, and K. Weinberger, “Simplifying graph convolutional networks,” in Proc. Int. Conf. Machine Learning, PMLR, 2019, pp. 6861–6871.
    [25]
    X. He, K. Deng, X. Wang, Y. Li, Y. Zhang, and M. Wang, “Lightgcn: Simplifying and powering graph convolution network for recommendation,” in Proc. 43rd Int. ACM SIGIR Conf. Research and Development in Information Retrieval, 2020, pp. 639–648.
    [26]
    H. Nt and T. Maehara, “Revisiting graph neural networks: All we have is low-pass filters,” arXiv preprint arXiv: 1905.09550, 2019.
    [27]
    Y. Yang, J. Qiu, M. Song, D. Tao, and X. Wang, “Distilling knowledge from graph convolutional networks,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition, 2020, pp. 7074–7083.
    [28]
    C. Yang, J. Liu, and C. Shi, “Extract the knowledge of graph neural networks and go beyond it: An effective knowledge distillation framework,” in Proc. Web Conf., 2021, pp. 1227–1237.
    [29]
    Z. Wu, S. Pan, F. Chen, G. Long, C. Zhang, and S. Y. Philip, “A comprehensive survey on graph neural networks,” IEEE Trans. Neural Networks and Learning Systems, vol. 32, no. 1, pp. 4–24, 2020.
    [30]
    Z. Zhang, P. Cui, and W. Zhu, “Deep learning on graphs: A survey,” arXiv preprint arXiv: 1812.04202, 2018.
    [31]
    S. Zhang, H. Tong, J. Xu, and R. Maciejewski, “Graph convolutional networks: A comprehensive review,” Computational Social Networks, vol. 6, no. 1, pp. 1–23, 2019. doi: 10.1186/s40649-019-0061-6
    [32]
    Y. LeCun and Y. Bengio, “Convolutional networks for images, speech, and time series,” The Handbook of Brain Theory and Neural Networks, vol. 3361, no. 10, Article No. 1995, 1995.
    [33]
    D. I. Shuman, S. K. Narang, P. Frossard, A. Ortega, and P. Vandergheynst, “The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains,” IEEE Signal Processing Magazine, vol. 30, no. 3, pp. 83–98, 2013. doi: 10.1109/MSP.2012.2235192
    [34]
    J. Gilmer, S. S. Schoenholz, P. F. Riley, O. Vinyals, and G. E. Dahl, “Neural message passing for quantum chemistry,” in Proc. Int. Conf. Machine Learning, PMLR, 2017, pp. 1263–1272.
    [35]
    W. L. Hamilton, R. Ying, and J. Leskovec, “Inductive representation learning on large graphs,” in Proc. 31st Int. Conf. Neural Information Processing Systems, 2017, pp. 1025–1035.
    [36]
    A. Qin, Z. Shang, J. Tian, Y. Wang, T. Zhang, and Y. Y. Tang, “Spectral–spatial graph convolutional networks for semisupervised hyperspectral image classification,” IEEE Geoscience and Remote Sensing Letters, vol. 16, no. 2, pp. 241–245, 2018.
    [37]
    C. Wang, B. Samari, and K. Siddiqi, “Local spectral graph convolution for point set feature learning,” in Proc. European Conf. Computer Vision (ECCV), 2018, pp. 52–66.
    [38]
    D. Valsesia, G. Fracastoro, and E. Magli, “Learning localized generative models for 3D point clouds via graph convolution,” in Proc. Int. Conf. Learning Representations, 2018, pp. 1–15.
    [39]
    Y. Wei, X. Wang, L. Nie, X. He, R. Hong, and T.-S. Chua, “Mmgcn: Multi-modal graph convolution network for personalized recommendation of micro-video,” in Proc. 27th ACM Int. Conf. Multimedia, 2019, pp. 1437–1445.
    [40]
    S. Cui, B. Yu, T. Liu, Z. Zhang, X. Wang, and J. Shi, “Edge-enhanced graph convolution networks for event detection with syntactic relation,” in Proc. Conf. Empirical Methods in Natural Language Processing: Findings, 2020, pp. 2329–2339.
    [41]
    Z. Liang, M. Yang, L. Deng, C. Wang, and B. Wang, “Hierarchical depthwise graph convolutional neural network for 3D semantic segmentation of point clouds,” in Proc. Int. Conf. Robotics and Automation (ICRA), IEEE, 2019, pp. 8152–8158.
    [42]
    H. Yang, “Aligraph: A comprehensive graph neural network platform,” in Proc. 25th ACM SIGKDD International Conf. Knowledge Discovery & Data Mining, 2019, pp. 3165–3166.
    [43]
    M. Yan, L. Deng, X. Hu, L. Liang, Y. Feng, X. Ye, Z. Zhang, D. Fan, and Y. Xie, “Hygcn: A gcn accelerator with hybrid architecture,” in Proc. IEEE Int. Symposium on High Performance Computer Architecture (HPCA), 2020, pp. 15–29.
    [44]
    R. Ying, R. He, K. Chen, P. Eksombatchai, W. L. Hamilton, and J. Leskovec, “Graph convolutional neural networks for web-scale recommender systems,” in Proc. 24th ACM SIGKDD Int. Conf. Knowledge Discovery & Data Mining, 2018, pp. 974–983.
    [45]
    K. Xu, W. Hu, J. Leskovec, and S. Jegelka, “How powerful are graph neural networks?” in Proc. Int. Conf. Learning Representations, 2019, pp. 1–17.
    [46]
    K. Xu, C. Li, Y. Tian, T. Sonobe, K.-i. Kawarabayashi, and S. Jegelka, “Representation learning on graphs with jumping knowledge networks,” in Proc. Int. Conf. Machine Learning, PMLR, 2018, pp. 5453– 5462.
    [47]
    H. Dai, Z. Kozareva, B. Dai, A. Smola, and L. Song, “Learning steady-states of iterative algorithms over graphs,” in Proc. Int. Conf. Machine Learning, PMLR, 2018, pp. 1106–1114.
    [48]
    J. Chen, J. Zhu, and L. Song, “Stochastic training of graph convolutional networks with variance reduction,” in Proc. Int. Conf. Machine Learning, 2018, pp. 941–949.
    [49]
    J. Chen, T. Ma, and C. Xiao, “Fastgcn: Fast learning with graph convolutional networks via importance sampling,” in Proc. Int. Conf. Learning Representations, 2018, pp. 1–15.
    [50]
    W. Huang, T. Zhang, Y. Rong, and J. Huang, “Adaptive sampling towards fast graph representation learning,” in Proc. Advances in Neural Information Processing Systems, 2018, vol.31, pp.4558–4567.
    [51]
    D. Zou, Z. Hu, Y. Wang, S. Jiang, Y. Sun, and Q. Gu, “Layer-dependent importance sampling for training deep and large graph convolutional networks,” Advances in Neural Information Processing Systems, vol. 32, pp. 11249–11259, 2019.
    [52]
    W.-L. Chiang, X. Liu, S. Si, Y. Li, S. Bengio, and C.-J. Hsieh, “Cluster-GCN: An efficient algorithm for training deep and large graph convolutional networks,” in Proc. 25th ACM SIGKDD Int. Conf. Knowledge Discovery & Data Mining, 2019, pp. 257–266.
    [53]
    H. Zeng, H. Zhou, A. Srivastava, R. Kannan, and V. Prasanna, “GraphSAINT: Graph sampling based inductive learning method,” in Proc. Int. Conf. Learning Representations, 2020, pp. 1–19.
    [54]
    J. Bai, Y. Ren, and J. Zhang, “Ripple walk training: A subgraph-based training framework for large and deep graph neural network,” arXiv preprint arXiv: 2002.07206, 2020.
    [55]
    H. Zeng, H. Zhou, A. Srivastava, R. Kannan, and V. Prasanna, “Accurate, efficient and scalable graph embedding,” in Proc. IEEE Int. Parallel and Distributed Processing Symposium (IPDPS), 2019, pp. 462–471.
    [56]
    A. Li, Z. Qin, R. Liu, Y. Yang, and D. Li, “Spam review detection with graph convolutional networks,” in Proc. 28th ACM Int. Conf. Information and Knowledge Management, 2019, pp. 2703–2711.
    [57]
    C. Zhang, D. Song, C. Huang, A. Swami, and N. V. Chawla, “Heterogeneous graph neural network,” in Proc. 25th ACM SIGKDD Int. Conf. Knowledge Discovery & Data Mining, 2019, pp. 793–803.
    [58]
    Z. Hu, Y. Dong, K. Wang, and Y. Sun, “Heterogeneous graph transformer,” in Proc. Web Conf., 2020, pp. 2704–2710.
    [59]
    H. Zhang and J. Zhang, “Text graph transformer for document classification,” in Proc. Conf. Empirical Methods in Natural Language Processing (EMNLP), 2020, pp. 8322–8327.
    [60]
    P. Sen, G. Namata, M. Bilgic, L. Getoor, B. Galligher, and T. Eliassi-Rad, “Collective classification in network data,” AI magazine, vol. 29, no. 3, pp. 93–93, 2008. doi: 10.1609/aimag.v29i3.2157
    [61]
    M. Zitnik and J. Leskovec, “Predicting multicellular function through multi-layer tissue networks,” Bioinformatics, vol. 33, no. 14, pp. i190–i198, 2017. doi: 10.1093/bioinformatics/btx252
    [62]
    J. McAuley, C. Targett, Q. Shi, and A. Van Den Hengel, “Image-based recommendations on styles and substitutes,” in Proc. 38th International ACM SIGIR Conf. Research and Development in Information Retrieval, 2015, pp. 43–52.
    [63]
    T. Mikolov, I. Sutskever, K. Chen, G. S. Corrado, and J. Dean, “Distributed representations of words and phrases and their compositionality,” in Proc. Advances in Neural Information Processing Systems, 2013, pp. 3111– 3119.
    [64]
    Y. Bengio, J. Louradour, R. Collobert, and J. Weston, “Curriculum learning,” in Proc. 26th Annual Int. Conf. Machine Learning, 2009, pp. 41–48.
    [65]
    C. Eksombatchai, P. Jindal, J. Z. Liu, Y. Liu, R. Sharma, C. Sugnet, M. Ulrich, and J. Leskovec, “PIXIE: A system for recommending 3+ billion items to 200+ million users in real-time,” in Proc. World Wide Web Conf., 2018, pp. 1775–1784.
    [66]
    Z. Liu, Z. Wu, Z. Zhang, J. Zhou, S. Yang, L. Song, and Y. Qi, “Bandit samplers for training graph neural networks,” arXiv preprint arXiv: 2006.05806, 2020.
    [67]
    G. Karypis and V. Kumar, “A fast and high quality multilevel scheme for partitioning irregular graphs,” SIAM Journal on Scientific Computing, vol. 20, no. 1, pp. 359–392, 1998. doi: 10.1137/S1064827595287997
    [68]
    I. S. Dhillon, Y. Guan, and B. Kulis, “Weighted graph cuts without eigenvectors a multilevel approach,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 29, no. 11, pp. 1944–1957, 2007. doi: 10.1109/TPAMI.2007.1115
    [69]
    B. Ribeiro and D. Towsley, “Estimating and sampling graphs with multidimensional random walks,” in Proc. 10th ACM SIGCOMM Conf. Internet Measurement, 2010, pp. 390–403.
    [70]
    J. Zhang, H. Zhang, C. Xia, and L. Sun, “Graph-bert: Only attention is needed for learning graph representations,” arXiv preprint arXiv: 2001.05140, 2020.
    [71]
    G. Li, M. Muller, A. Thabet, and B. Ghanem, “Deepgcns: Can GCNs go as deep as CNNs?” in Proc. IEEE/CVF Int. Conf. Computer Vision, 2019, pp. 9267–9276.
    [72]
    Q. Li, Z. Han, and X.-M. Wu, “Deeper insights into graph convolutional networks for semi-supervised learning,” in Proc. 32nd AAAI Conf. Artificial Intelligence, 2018, pp. 3538–3545.
    [73]
    W. Cong, R. Forsati, M. Kandemir, and M. Mahdavi, “Minimal variance sampling with provable guarantees for fast training of graph neural networks,” in Proc. 26th ACM SIGKDD Int. Conf. Knowledge Discovery & Data Mining, 2020, pp. 1393– 1403.
    [74]
    Q. Cheng, M. Wen, J. Shen, D. Wang, and C. Zhang, “Towards a deep-pipelined architecture for accelerating deep GCN on a multi-FPGA platform,” in Proc. Int. Conf. Algorithms and Architectures for Parallel Processing, Springer, 2020, pp. 528–547.
    [75]
    B. Zhang, H. Zeng, and V. Prasanna, “Hardware acceleration of large scale GCN inference,” in Proc. 31st IEEE Int. Conf. Application-Specific Systems, Architectures and Processors (ASAP), 2020, pp. 61–68.
    [76]
    B. Zhang, H. Zeng, and V. Prasanna, “Accelerating large scale GCN inference on FPGA,” in Proc. 28th IEEE Annual Int. Symposium on Field-Programmable Custom Computing Machines (FCCM), 2020, pp. 241–241.
    [77]
    Y. Meng, S. Kuppannagari, and V. Prasanna, “Accelerating proximal policy optimization on CPU-FPGA heterogeneous platforms,” in Proc. 28th IEEE Annual Int. Symposium on Field-Programmable Custom Computing Machines (FCCM), 2020, pp. 19–27.
    [78]
    H. Zeng and V. Prasanna, “Graphact: Accelerating gcn training on cpu-fpga heterogeneous platforms,” in Proc. ACM/SIGDA Int. Symposium on Field-Programmable Gate Arrays, 2020, pp. 255–265.
    [79]
    T. Geng, A. Li, R. Shi, C. Wu, T. Wang, Y. Li, P. Haghi, A. Tumeo, S. Che, S. Reinhardt, and M. C. Herbordt, “AWB-GCN: A graph convolutional network accelerator with runtime workload rebalancing,” in Proc. 53rd Annual IEEE/ACM Int. Symposium on Microarchitecture (MICRO), IEEE, 2020, pp. 922–936.
    [80]
    A. Auten, M. Tomei, and R. Kumar, “Hardware acceleration of graph neural networks,” in Proc. 57th ACM/IEEE Design Automation Conf. (DAC), IEEE, 2020, pp. 1–6.
    [81]
    S. Liang, Y. Wang, C. Liu, L. He, L. Huawei, D. Xu, and X. Li, “Engn: A high-throughput and energy-efficient accelerator for large graph neural networks,” IEEE Trans. Computers, vol. 70, no. 9, pp. 1511–1525, 2020.
    [82]
    K. Kiningham, C. Re, and P. Levis, “GRIP: A graph neural network accelerator architecture,” arXiv preprint arXiv: 2007.13828, 2020.
    [83]
    F. Zhang, X. Liu, J. Tang, Y. Dong, P. Yao, J. Zhang, X. Gu, Y. Wang, B. Shao, R. Li, and K. Wang, “OAG: Toward linking large-scale heterogeneous entity graphs,” in Proc. 25th ACM SIGKDD Int. Conf. Knowledge Discovery & Data Mining, 2019, pp. 2585–2595.
    [84]
    R. Hussein, D. Yang, and P. Cudré-Mauroux, “Are meta-paths necessary? revisiting heterogeneous graph embeddings,” in Proc. 27th ACM Int. Conf. Information and Knowledge Management, 2018, pp. 437–446.
    [85]
    H.-C. Shin, H. R. Roth, M. Gao, L. Lu, Z. Xu, I. Nogues, J. Yao, D. Mollura, and R. M. Summers, “Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning,” IEEE Trans. Medical Imaging, vol. 35, no. 5, pp. 1285–1298, 2016. doi: 10.1109/TMI.2016.2528162
    [86]
    K. Zhang, W. Zuo, Y. Chen, D. Meng, and L. Zhang, “Beyond a Gaussian denoiser: Residual learning of deep CNN for image denoising,” IEEE Trans. Image Processing, vol. 26, no. 7, pp. 3142–3155, 2017. doi: 10.1109/TIP.2017.2662206
    [87]
    K. Zhang, W. Zuo, S. Gu, and L. Zhang, “Learning deep CNN denoiser prior for image restoration,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2017, pp. 3929–3938.
    [88]
    Y. Rong, W. Huang, T. Xu, and J. Huang, “Dropedge: Towards deep graph convolutional networks on node classification,” in Proc. Int. Conf. Learning Representations, 2020, pp. 1–17.
    [89]
    K. Oono and T. Suzuki, “Graph neural networks exponentially lose expressive power for node classification,” in Proc. Int. Conf. Learning Representations, 2020, pp. 1–37.
    [90]
    A. Hasanzadeh, E. Hajiramezanali, S. Boluki, M. Zhou, N. Duffield, K. Narayanan, and X. Qian, “Bayesian graph neural networks with adaptive connection sampling,” in Proc. Int. Conf. Machine Learning, PMLR, 2020, pp. 4094–4104.
    [91]
    S. Abu-El-Haija, B. Perozzi, A. Kapoor, N. Alipourfard, K. Lerman, H. Harutyunyan, G. Ver Steeg, and A. Galstyan, “Mixhop: Higher-order graph convolutional architectures via sparsified neighborhood mixing,” in Proc. International Conf. Machine Learning, PMLR, 2019, pp. 21–29.
    [92]
    S. Luan, M. Zhao, X.-W. Chang, and D. Precup, “Break the ceiling: Stronger multi-scale deep graph convolutional networks,” in Proc. Advances in Neural Information Processing Systems, 2019, vol.32, pp. 10945–10955.
    [93]
    M. Liu, H. Gao, and S. Ji, “Towards deeper graph neural networks,” in Proc. 26th ACM SIGKDD Int. Conf. Knowledge Discovery & Data Mining, 2020, pp. 338–348.
    [94]
    H. Zeng, M. Zhang, Y. Xia, A. Srivastava, A. Malevich, R. Kannan, V. Prasanna, L. Jin, and R. Chen, “Deep graph neural networks with shallow subgraph samplers,” arXiv preprint arXiv: 2012.01380, 2020.

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Figures(7)  / Tables(14)

    Article Metrics

    Article views (2569) PDF downloads(253) Cited by()

    Highlights

    • We provide the first comprehensive taxonomy of sampling methods for efficient GCN training
    • We compare sampling methods from multiple aspects and highlight their characteristics
    • We analyze multiple categories of sampling methods in theoretical and experimental manner

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return