Abstract
Graph convolutional network (GCN) has led to state-of-the-art performance for structured data. The superior performance would be partly due to the convolutional operations that operate over local neighborhoods. However, the distant long-range dependencies in data are still challenging to capture since it requires deep stacks of convolutional operations. Moreover, missing links in structured data might further hurt the performance. This paper introduces non-locality augmented graph convolution blocks into GCN to capture long-range or even disconnected dependencies. Specifically, we propose a dictionary-based non-locality encoding approach in which the non-local information is encoded by both graph convolution and dictionary-based implicit convolution. Unlike previous non-local approaches, our non-local block does not rely on the exhaustive computation of the relationship of data pairs. Thus, it is suitable for GCN, which typically models a large number of data samples. What’s more, the proposed non-local blocks could be embedded into arbitrarily GCN architectures. We demonstrate the efficacy of our non-local block on four benchmark datasets.
Similar content being viewed by others
Data Availability
The datasets analyzed during the current study are publically available. Cora, CiteSeer, and PubMed: http://linqs.umiacs.umd.edu/projects//projects/lbc/. Ogbn-arxiv: https://ogb.stanford.edu/docs/nodeprop/.
References
Z. Aslan, Deep convolutional neural network-based framework in the automatic diagnosis of migraine. Circuits Syst. Signal Process. 42(5), 3054–3071 (2023). https://doi.org/10.1007/s00034-022-02265-3
J. Atwood, D. Towsley, Diffusion-convolutional neural networks. In: NeurIPS (2016), pp. 1993–2001. https://doi.org/10.48550/arXiv.1511.02136
Z. Bai, Q. Ding, H. Xu, J. Chi, X. Zhang, T. Sun, Skeleton-based similar action recognition through integrating the salient image feature into a center-connected graph convolutional network. Neurocomputing 507, 40–53 (2022). https://doi.org/10.1016/j.neucom.2022.07.080
M. Belkin, P. Niyogi, V. Sindhwani, Manifold regularization: a geometric framework for learning from labeled and unlabeled examples. J. Mach. Learn. Res. 7(11), 2399–2434 (2006). https://doi.org/10.1007/s10846-006-9077-x
J. Bruna, W. Zaremba, A. Szlam, Y. LeCun, Spectral networks and locally connected networks on graphs. In ICLR (2014). https://doi.org/10.48550/arXiv.1312.6203
A. Buades, B. Coll, J.M. Morel, A non-local algorithm for image denoising. In CVPR (2005), pp. 60–65. https://ieeexplore.ieee.org/document/1467423/
T. Cai, S. Luo, K. Xu, D. He, T.y. Liu, L. Wang, Graphnorm: a principled approach to accelerating graph neural network training. In International Conference on Machine Learning (PMLR, 2021), pp. 1204–1215. https://doi.org/10.48550/arXiv.2009.03294
H. Chen, Z. Huang, Y. Xu, Z. Deng, F. Huang, P. He, Z. Li, Neighbor enhanced graph convolutional networks for node classification and recommendation. Knowl. Based Syst. 246, 108594 (2022). https://doi.org/10.48550/arXiv.2203.16097
K.J. Chen, H. Lu, Z. Liu, J. Zhang, Heterogeneous graph convolutional network with local influence. Knowl. Based Syst. 236, 107699 (2022). https://doi.org/10.1016/j.knosys.2021.107699
M. Defferrard, X. Bresson, P. Vandergheynst, Convolutional neural networks on graphs with fast localized spectral filtering. In: NeurIPS. pp. 3844–3852 (2016), https://dl.acm.org/doi/10.5555/3157382.3157527
Q. Du, M. Gunzburger, R.B. Lehoucq, K. Zhou, Analysis and approximation of nonlocal diffusion problems with volume constraints. SIAM Rev. 54(4), 667–696 (2012). https://doi.org/10.1137/110833294
D.K. Duvenaud, D. Maclaurin, J. Iparraguirre, R. Bombarell, T. Hirzel, A. Aspuru-Guzik, R.P. Adams, Convolutional networks on graphs for learning molecular fingerprints. In NeurIPS (2015), pp. 2224–2232. https://doi.org/10.48550/arXiv.1509.09292
Y. Feng, H. You, Z. Zhang, R. Ji, Y. Gao, Hypergraph neural networks. In AAAI vol. 33 (2019), pp. 3558–3565. https://doi.org/10.1609/aaai.v33i01.33013558
M. Ghorvei, M. Kavianpour, M.T. Beheshti, A. Ramezani, Spatial graph convolutional neural network via structured subdomain adaptation and domain adversarial learning for bearing fault diagnosis. Neurocomputing 517, 44–61 (2023). https://doi.org/10.1016/j.neucom.2022.10.057
W. Hamilton, Z. Ying, J. Leskovec, Inductive representation learning on large graphs. In NeurIPS (2017), pp. 1024–1034. https://doi.org/10.48550/arXiv.1706.02216
W. Hu, M. Fey, M. Zitnik, Y. Dong, H. Ren, B. Liu, M. Catasta, J. Leskovec, Open graph benchmark: datasets for machine learning on graphs. In NeurIPS (2020). https://doi.org/10.48550/arXiv.2005.00687
S. Jamali Golzar, G. Karimian, M. Shoaran, M. Fattahi Sani, DGCNN on FPGA: acceleration of the point cloud classifier using FPGAS. Circuits Syst. Signal Process. 42(2), 748–779 (2023). https://doi.org/10.1007/s00034-022-02179-0
J. Jiang, Y. Wei, Y. Feng, J. Cao, Y. Gao, Dynamic hypergraph neural networks. In IJCAI (2019), pp. 2635–2641. https://doi.org/10.5555/3367243.3367406
D.P. Kingma, J. Ba, Adam: A method for stochastic optimization. In ICLR (2015). https://doi.org/10.48550/arXiv.1412.6980
T.N. Kipf, M. Welling, Semi-supervised classification with graph convolutional networks. In ICLR (2017). https://doi.org/10.48550/arXiv.1609.02907
B. Lei, Y. Zhu, S. Yu, H. Hu, Y. Xu, G. Yue, T. Wang, C. Zhao, S. Chen, P. Yang et al., Multi-scale enhanced graph convolutional network for mild cognitive impairment detection. Pattern Recogn. 134, 109106 (2023). https://doi.org/10.1016/j.patcog.2022.109106
R. Levie, F. Monti, X. Bresson, M.M. Bronstein, Cayleynets: graph convolutional neural networks with complex rational spectral filters. IEEE TSP 67(1), 97–109 (2018). https://doi.org/10.1109/TSP.2018.2879624
T. Liang, L. Ma, W. Zhang, H. Xu, C. Xia, Y. Yin, Content-aware recommendation via dynamic heterogeneous graph convolutional network. Knowl. Based Syst. 251, 109185 (2022). https://doi.org/10.1016/j.knosys.2022.109185
Y. Lin, S. Li, J. Xu, J. Xu, D. Huang, W. Zheng, Y. Cao, J. Lu, Graph over-parameterization: Why the graph helps the training of deep graph convolutional network. Neurocomputing 534, 77–85 (2023). https://doi.org/10.1016/j.neucom.2023.02.054
Q. Lu, L. Getoor, Link-based classification. In ICML (2003), pp. 496–503. https://doi.org/10.1007/1-84628-284-5_7
Y. Meng, J. Bridge, C. Addison, M. Wang, C. Merritt, S. Franks, M. Mackey, S. Messenger, R. Sun, T. Fitzmaurice et al., Bilateral adaptive graph convolutional network on CT based COVID-19 diagnosis with uncertainty-aware consensus-assisted multiple instance learning. Med. Image Anal. 84, 102722 (2023). https://doi.org/10.1016/j.media.2022.102722
A. Micheli, Neural network for graphs: a contextual constructive approach. IEEE TNN 20(3), 498–511 (2009). https://doi.org/10.1109/TNN.2008.2010350
F. Monti, D. Boscaini, J. Masci, E. Rodola, J. Svoboda, M.M. Bronstein, Geometric deep learning on graphs and manifolds using mixture model CNNs. In CVPR (2017), pp. 5115–5124. https://doi.org/10.1109/CVPR.2017.576
B. Perozzi, R. Al-Rfou, S. Skiena, Deepwalk: online learning of social representations. In KDD (2014) pp. 701–710. https://doi.org/10.1145/2623330.2623732
G. Puvaneswari, Test node selection for fault diagnosis in analog circuits using faster rcnn model. Circuits Syst. Signal Process. (2023) pp. 1–26. https://doi.org/10.1007/s00034-022-02276-0
G.K. Sahoo, S.K. Das, P. Singh, Performance comparison of facial emotion recognition: a transfer learning-based driver assistance framework for in-vehicle applications. Circuits Syst. Signal Process. (2023), pp. 1–28. https://doi.org/10.1007/s00034-023-02320-7
P. Sen, G. Namata, M. Bilgic, L. Getoor, B. Galligher, T. Eliassi-Rad, Collective classification in network data. AI Mag. 29(3), 93–93 (2008). https://doi.org/10.1609/aimag.v29i3.2157
S.A. Silling, Reformulation of elasticity theory for discontinuities and long-range forces. J. Mech. Phys. Solids 48(1), 175–209 (2000). https://doi.org/10.1016/S0022-5096(99)00029-0
Y. Tao, Q. Sun, Q. Du, W. Liu, Nonlocal neural networks, nonlocal diffusion and nonlocal modeling. In NeurIPS (2018), pp. 496–506. https://doi.org/10.48550/arXiv.1806.00681
P. Veličković, G. Cucurull, A. Casanova, A. Romero, P. Lio, Y. Bengio, Graph attention networks. In ICLR (2018). https://doi.org/10.48550/arXiv.1710.10903
X. Wang, R. Girshick, A. Gupta, K. He, Non-local neural networks. In CVPR (2018), pp. 7794–7803. https://doi.org/10.48550/arXiv.1711.07971
Z. Wu, S. Pan, F. Chen, G. Long, C. Zhang, P.S. Yu, A comprehensive survey on graph neural networks. IEEE TNNLS 32(1), 4–24 (2020). https://doi.org/10.1109/TNNLS.2020.2978386
B. Xu, H. Shen, Q. Cao, K. Cen, X. Cheng, Graph convolutional networks using heat kernel for semi-supervised learning. arXiv:2007.16002 (2020). https://doi.org/10.48550/arXiv.2007.16002
Z. Yang, W.W. Cohen, R. Salakhutdinov, Revisiting semi-supervised learning with graph embeddings. In: ICML (2016), pp. 40–48. https://doi.org/10.48550/arXiv.1603.08861
H. You, T. Geng, Y. Zhang, A. Li, Y. Lin, Gcod: Graph convolutional network acceleration via dedicated algorithm and accelerator co-design. In 2022 IEEE International Symposium on High-Performance Computer Architecture (HPCA) (IEEE, 2022), pp. 460–474. https://doi.org/10.48550/arXiv.2112.11594
Y. Zhang, N. Wang, Y. Chen, C. Zou, H. Wan, X. Zhao, Y. Gao, Hypergraph label propagation network. In AAAI (2020), pp. 6885–6892. https://doi.org/10.1609/aaai.v34i04.6170
M. Zhao, S. Dai, Y. Zhu, H. Tang, P. Xie, Y. Li, C. Liu, B. Zhang, PB-GCN: Progressive binary graph convolutional networks for skeleton-based action recognition. Neurocomputing 501, 640–649 (2022). https://doi.org/10.1016/j.neucom.2022.06.070
X. Zhu, Z. Ghahramani, J.D. Lafferty, Semi-supervised learning using gaussian fields and harmonic functions. In ICML (2003), pp. 912–919. https://i.cs.hku.hk/fyp/2016/fyp16005/file/References/1_graph.pdf
Acknowledgements
The research was supported by the National Natural Science Foundation of China under Grant No. 62072468, the Natural Science Foundation of Shandong Province, China (Grant No. ZR2019MF073), the Fundamental Research Funds for the Central Universities, China University of Petroleum (East China) (Grant No. 20CX05001A), the Major Scientific and Technological Projects of CNPC (No. ZD2019-183-008) and the Creative Research Team of Young Scholars at Universities in Shandong Province (No. 2019KJN019), the Major Basic Research Projects in Shandong Province (Grant No. ZR2023ZD32), the National Natural Science Foundation of China (Grant No. 62372468), the State Key Laboratory of Shale Oil and Gas Enrichment Mechanisms and Effective Development(Grant No. 33550000-22-ZC0613-0243), the Shandong Natural Science Foundation (Grant No. ZR2023MF008), and the Qingdao Natural Science Foundation (Grant No. 23-2-1-161-zyyd-jch).
Author information
Authors and Affiliations
Contributions
CD contributed to methodology, design experimental program, and writing—original draft; SS was involved in data preprocessing and writing—original draft and provided software; JT and XS contributed to formal analysis and investigation; WL was involved in resources and supervision; and YW and BL were involved in conceptualization, funding acquisition, resources, supervision, and writing—review and editing.
Corresponding authors
Ethics declarations
Conflict of interest
The authors declare no conflict of interest in this work.
Ethical Approval
This article does not contain any studies with human participants or animals performed by any of the authors.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Du, C., Shao, S., Tang, J. et al. Non-local Graph Convolutional Network. Circuits Syst Signal Process 43, 2095–2114 (2024). https://doi.org/10.1007/s00034-023-02563-4
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00034-023-02563-4