Abstract
Recently, graph neural networks have achieved good performance in graph representation learning. However, most graph neural networks only utilize node low-frequency signals and destroy node similarity when aggregating graph structure and node features, which limits their ability to represent graph-structured data. Therefore, we propose a node similarity preserving graph convolutional network based on full-frequency information (FSP-GCN). It extracts relevant information to the greatest extent from graph structure and node features while preserving node similarity for aggregation. Precisely, to better capture full-frequency information, we propose an improved aggregation component called MFGCN that adopts a multi-head attention mechanism to integrate signals in different frequency domains adaptively. Then we design a node similarity aggregation method to aggregate a k-nearest neighbor(kNN) graph constructed from the original graph with the feature graph learned from the MFGCN aggregation component to preserve node similarity. Finally, we employ contrastive learning to preserve node similarity further. We also compare the performance of the FSP-GCN model with that of ten real-world networks, using well-known assortative and disassortative datasets. The results demonstrate that FSP-GCN offers significant performance improvement compared to representative baselines. In addition, extensive comparative experiments are conducted on the robustness of the model and alleviating the over-smoothing problem. The results show that the FSP-GCN model can effectively alleviate the over-smoothing problem and resist the adversarial attack of the graph structure.
Similar content being viewed by others
References
Tang J, Sun J, Wang C, Yang, Z (2009) Social influence analysis in large-scale networks. In: Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. KDD ’09, pp 807–816. Association for Computing Machinery, New York, NY, USA. https://doi.org/10.1145/1557019.1557108
Wu Z, Pan S, Chen F, Long G, Zhang C, Yu PS (2021) A comprehensive survey on graph neural networks. IEEE Trans Neural Netw Learn Syst 32(1):4–24. https://doi.org/10.1109/TNNLS.2020.2978386
Liu M, Wang Z, Ji S (2021) Non-local graph neural networks. IEEE Trans Pattern Anal Mach Intell 1:1. https://doi.org/10.1109/tpami.2021.3134200
Zhang M, Chen Y (2018) Link prediction based on graph neural networks. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems. NIPS’18, pp 5171–5181. Curran Associates Inc., Red Hook, NY, USA. https://doi.org/10.48550/arXiv.1802.09691
Knyazev B, Taylor GW, Amer MR (2019) Understanding attention and generalization in graph neural networks. Curran Associates Inc., Red Hook
Yao L, Mao C, Luo Y (2019) Graph convolutional networks for text classification. Proc AAAI Conf Artif Intell 33(01):7370–7377. https://doi.org/10.1609/aaai.v33i01.33017370
He X, Deng K, Wang X, Li Y, Zhang Y, Wang M (2020) LightGCN: simplifying and powering graph convolution network for recommendation, pp 639–648. association for computing machinery, New York, NY, USA. https://doi.org/10.1145/3397271.3401063
Zeng F, Chen N, Yang D (2022) Simplified-boosting ensemble convolutional network for text classification. Neural Process Lett. https://doi.org/10.1007/s11063-022-10843-4
Bongini P, Bianchini M, Scarselli F (2021) Molecular generative graph neural networks for drug discovery. Neurocomputing 450:242–252. https://doi.org/10.1016/j.neucom.2021.04.039
Jin D, Liu Z, Li W, He D, Zhang W (2019) Graph convolutional networks meet markov random fields: Semi-supervised community detection in attribute networks. Proc AAAI Conf Artif Intell 33(01):152–159. https://doi.org/10.1609/aaai.v33i01.3301152
Defferrard M, Bresson X, Vandergheynst P (2016) Convolutional neural networks on graphs with fast localized spectral filtering. In: Proceedings of the 30th International Conference on Neural Information Processing Systems. NIPS’16, pp 3844–3852, Red Hook, NY, USA
Hamilton WL, Ying R, Leskovec J (2017) Inductive representation learning on large graphs. In: Proceedings of the 31st International Conference on Neural Information Processing Systems. NIPS’17, pp 1025–1035, Red Hook, NY, USA
Kipf TN, Welling M (2016) Semi-supervised classification with graph convolutional networks. https://doi.org/10.48550/arXiv.1609.02907
Gilmer J, Schoenholz SS, Riley PF, Vinyals O, Dahl GE (2017) Neural message passing for quantum chemistry. In: Proceedings of the 34th International Conference on Machine Learning - Volume 70. ICML’17, pp 1263–1272. JMLR.org, ???
Wu F, Souza A, Zhang T, Fifty C, Yu T, Weinberger K (2019) Simplifying graph convolutional networks. In: International Conference on Machine Learning, pp 6861–6871. PMLR
Li Q, Wu X-M, Liu H, Zhang X, Guan Z (2019) Label efficient semi-supervised learning via graph filtering. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Bruna J, Zaremba W, Szlam A, Lecun Y (2014) Spectral networks and locally connected networks on graphs. In: International Conference on Learning Representations (ICLR2014), CBLS, April 2014
Xu B, Shen H, Cao Q, Cen K, Cheng X (2020) Graph convolutional networks using heat kernel for semi-supervised learning. https://doi.org/10.48550/ARXIV.2007.16002
Ribeiro LFR, Saverese PHP, Figueiredo DR (2017) struc2vec: Learning node representations from structural identity. In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. KDD ’17, pp 385–394. Association for Computing Machinery, New York, NY, USA. https://doi.org/10.1145/3097983.3098061
Newman MEJ (2003) Mixing patterns in networks. Phys Rev E 67:026126. https://doi.org/10.1103/PhysRevE.67.026126
Zhu J, Yan Y, Zhao L, Heimann M, Akoglu L, Koutra D (2020) Beyond homophily in graph neural networks: Current limitations and effective designs. NIPS’20, vol 33, pp 7793–7804. https://doi.org/10.48550/arXiv.2006.11468
Zügner D, Akbarnejad A, Günnemann S (2018) Adversarial attacks on neural networks for graph data. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. KDD ’18, pp 2847–2856. Association for Computing Machinery, New York, NY, USA. https://doi.org/10.1145/3219819.3220078
Jin W, Derr T, Wang Y, Ma Y, Liu Z, Tang J (2021) Node similarity preserving graph convolutional networks. In: Proceedings of the 14th ACM International Conference on Web Search and Data Mining. WSDM ’21, pp 148–156. Association for Computing Machinery, New York, NY, USA. https://doi.org/10.1145/3437963.3441735
Bo D, Wang X, Shi C, Shen H (2021) Beyond low-frequency information in graph convolutional networks. Proceedings of the AAAI Conference on Artificial Intelligence 35(5):3950–3957. https://doi.org/10.48550/arXiv.2101.00797
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser Ł, Polosukhin I (2017) Attention is all you need. Adv Neural Inf Process Syst 30:541 arXiv:1706.03762
Bruna J, Zaremba W, Szlam A, LeCun Y (2013) Spectral networks and locally connected networks on graphs. https://doi.org/10.48550/arXiv.1312.6203
Xu B, Cen K, Huang J, Shen H, Cheng X (2020) A survey on graph convolutional neural network. Chin J Computers 43(5):26. https://doi.org/10.11897/SP.J.1016.2020.00755
Veličković P, Cucurull G, Casanova A, Romero A, Liò P, Bengio Y (2017) Graph attention networks. https://doi.org/10.48550/ARXIV.1710.10903
Wu Z, Lin Y, Wang J, Gregory S (2016) Link prediction with node clustering coefficient. Physica A: Stat Mech Appl 452(C):1–8. https://doi.org/10.5555/3327345.3327423
Cai H, Zheng VW, Chang KC-C (2018) A comprehensive survey of graph embedding: Problems, techniques, and applications. IEEE Trans Knowl Data Eng 30(9):1616–1637. https://doi.org/10.1109/TKDE.2018.2807452
Coşkun M, Koyutürk M (2021) Node similarity-based graph convolution for link prediction in biological networks. Bioinformatics 37(23):4501–4508. https://doi.org/10.1093/bioinformatics/btab464
Mnih V, Heess N, Graves A, kavukcuoglu k (2014) Recurrent models of visual attention. In: Proceedings of the 27th International Conference on Neural Information Processing Systems - Volume 2. NIPS’14, vol 27, pp 2204–2212. MIT Press, Cambridge, MA, USA. https://doi.org/10.5555/2969033.2969073
Bahdanau D, Cho K, Bengio Y (2014) Neural machine translation by jointly learning to align and translate. https://doi.org/10.48550/ARXIV.1409.0473
Yin W, Schütze H, Xiang B, Zhou B (2016) Abcnn: attention-based convolutional neural network for modeling sentence pairs. Trans Assoc Comput Linguistics 4:259–272. https://doi.org/10.48550/arXiv.1512.05193
Zhang L, Song H, Aletras N, Lu H (2022) Node-feature convolution for graph convolutional networks. Pattern Recognit 128:108661. https://doi.org/10.1016/j.patcog.2022.108661
Cui G, Zhou JSGCN, Yang C, Liu Z (2020) Adaptive graph encoder for attributed graph embedding. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. KDD ’20, pp 976–985. Association for Computing Machinery, New York, NY, USA. https://doi.org/10.1145/3394486.3403140
Leskovec KXWHJ, Jegelka S (2019) How powerful are graph neural networks. ICLR. Keyulu Xu Weihua Hu Jure Leskovec and Stefanie Jegelka
Dong W, Charikar M, Li K (2011) Efficient k-nearest neighbor graph construction for generic similarity measures, pp 577–586. https://doi.org/10.1145/1963405.1963487
Pei H, Wei B, Chang KC-C, Lei Y, Yang B (2020) Geom-gcn: Geometric graph convolutional networks. In: International Conference on Learning Representations. https://doi.org/10.1109/IJCNN48605.2020.9207639
Zhu X, Ghahramani Z, Lafferty JD (2003) Semi-supervised learning using gaussian fields and harmonic functions. In: Proceedings of the 20th International Conference on Machine Learning (ICML-03), pp. 912–919
Xu K, Li C, Tian Y, Sonobe T, Kawarabayashi K, Jegelka S (2018) Representation learning on graphs with jumping knowledge networks. Proceedings of the 35th International Conference on Machine Learning, 5453–5462. https://doi.org/10.48550/arXiv.1806.03536. PMLR
Chen M, Wei Z, Huang Z, Ding B, Li Y (2020) Simple and deep graph convolutional networks, 1725–1735. https://doi.org/10.48550/arXiv.2007.02133. PMLR
Klicpera J, Bojchevski A, Günnemann S (2018) Predict then propagate: graph neural networks meet personalized pagerank. http://arxiv.org/abs/1810.05997
Chien E, Peng J, Li P, Milenkovic, O (2020) Adaptive universal generalized pagerank graph neural network. http://arxiv.org/abs/2006.07988
Zügner D, Günnemann S (2019) Adversarial attacks on graph neural networks via meta learning. ACM Trans Knowl Discov Data 14:5. https://doi.org/10.1145/3394520
Wu H, Wang C, Tyshetskiy Y, Docherty A, Lu K, Zhu L (2019) Adversarial examples for graph data: deep insights into attack and defense. In: Proceedings of the 28th International Joint Conference on Artificial Intelligence, pp 4816–4823. https://doi.org/10.24963/ijcai.2019/669
Author information
Authors and Affiliations
Corresponding author
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
Li, Y., Liao, J., Liu, C. et al. Node Similarity Preserving Graph Convolutional Network Based on Full-frequency Information for Node Classification. Neural Process Lett 55, 5473–5498 (2023). https://doi.org/10.1007/s11063-022-11094-z
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-022-11094-z