Abstract
Graph neural networks (GNN) have achieved remarkable success by combining feature and structure information. However, the over-smoothing phenomenon has always been a crucial issue in GNN models since the node representation will easily converge to the full graph representation with the increasing of convolutional layers. Our investigation also indicates that the isolated part significantly restricts the capability due to the meaningless structure and local over-smoothing problem. While current models treated all nodes as equal with the absence of effectiveness of structure at different locations. To facilitate this line of research, we innovatively propose the graph neural network with feature enhancement of isolated parts (GNN-FEIP) consisting of graph partition, graph construction, and strategic label propagation procedures. In GNN-FEIP architecture, all the nodes are partitioned into several groups according to their position and connectivity. The feature-level similarity graph is reconstructed for subsequent feature enhancement of isolated nodes. Afterward, the preliminary prediction of the original GNN model has been adjusted with the strategic label propagation, which both balances the feature and structure of the nodes at different positions in a comprehensive manner. The exhaustive experiments indicate that GNN-FEIP achieves impressive performance than other off-the-shelf models, especially in the case that the isolated part is of large proportion.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Guo Z, Wang H (2021) A deep graph neural network-based mechanism for social recommendations. IEEE Trans Industrial Inform 17(4):2776–2783
Wang JH, Guo Y, Wen XX et al (2020) Improving graph-based label propagation algorithm with group partition for fraud detection. Appl Intell 50(10):3291–3300
Khan A, Golab L, Kargar M et al (2020) Compact group discovery in attributed graphs and social networks. Inf Process Manag 57(2):102054
Sun K, Lin ZC, Zhu ZX (2020) Multi-stage self-supervised learning for graph convolutional networks on graphs with few labeled nodes. In: AAAI Conference on Artificial Intelligence, pp. 5892–5899
Pedronette DCG, Latecki LJ (2021) Rank-based self-training for graph convolutional networks. Inf Process Manag 58(2):102443
Scarselli F, Gori M, Tsoi AC et al (2008) The graph neural network model. IEEE Trans Neural Netw 20(1):61–80
Zhang YL, Rohe K (2018) Understanding regularized spectral clustering via graph conductance. In: Neural Information Processing Systems, pp. 10631–10640
Li PZ, Huang L, Wang CD, et al (2019) EdMot: an edge enhancement approach for motif-aware community detection. In: Knowledge Discovery and Data Mining, pp. 479–487
Yan YW, Bian YC, Luo DS et al (2019) Constrained local graph clustering by colored random walk. World Wide Web Conference, In, pp 2137–2146
Seyedi SA, Lotfi A, Moradi P et al (2019) Dynamic graph-based label propagation for density peaks clustering. Expert Syst Appl 115:314–328
Ribeiro LFR, Saverese PH, Figueiredo DR (2017) Struc2vec: learning node representations from structural identity. In: Knowledge Discovery and Data Mining, pp. 385–394
Tang J, Qu M, Mei QZ, et al (2015) PTE: predictive text embedding through large-scale heterogeneous text networks. In: Knowledge Discovery and Data Mining, pp. 1165–1174
Qiu JZ, Dong YX, Ma H, et al (2018) Network embedding as matrix factorization: unifying DeepWalk, LINE, PTE, and Node2vec. In: Web Search and Data Mining, pp. 459–467
Bruna J, Zaremba W, Szlam A, et al (2014) Spectral networks and deep locally connected networks on graphs. In: International Conference on Learning Representations
Henaff M, Bruna J, Lecun Y (2015) Deep convolutional networks on graph-structured data. CoRR arXiv 1506:05163
Defferrard M, Bresson X, Vandergheynst P (2016) Convolutional neural networks on graphs with fast localized spectral filtering. In: Neural Information Processing Systems, pp. 3837–3845
Kipf TN, Welling M (2017). Semi-supervised classification with graph convolutional networks. In: International Conference on Learning Representations
Xu BB, Shen HW, Cao Q, et al (2019) Graph convolutional networks using heat kernel for semi-supervised learning. In: International Joint Conference on Artificial Intelligence, pp. 1928–1934
Klicpera J, Bojchevski A, Günnemann S (2019) Predict then propagate: graph neural networks meet personalized pagerank. In: International Conference on Learning Representations
Chen M, Wei ZW, Huang ZF (2020) simple and deep graph convolutional networks. In: International Conference on Machine Learning, pp 1725-1735
Xu BB, Shen HW, Cao Q, et al (2019) Graph wavelet neural network. In: International Conference on Learning Representations
Wu F, Zhang T, Souza AH, et al (2019) Simplifying graph convolutional networks. In: International Conference on Machine Learning, pp. 6861–6871
Hamilton WL, Ying ZT, Leskovec J (2017) Inductive representation learning on large graphs. In: Advances in Neural Information Processing Systems, pp. 1024–1034
Veličković P, Cucurull G, Casanova A, et al (2017) Graph attention networks. In: International Conference on Learning Representations
Vashishth S, Yadav P, Bhandari M, et al (2019) Confidence-based graph convolutional networks for semi-supervised learning. In: AISTATS, pp. 1792–1801
Chen J, Ma TF, Xiao C, et al (2018) FastGCN: fast learning with graph convolutional networks via importance sampling. In: International Conference on Learning Representations
Huang WB, Zhang T, Rong Y, et al (2018) Adaptive sampling towards fast graph representation learning. In: Neural Information Processing Systems, pp. 4558–4567
Rong Y, Huang WB, Xu TY, et al (2020) DropEdge: towards deep graph convolutional networks on node classification. In: International Conference on Learning Representations
Xu K, Li CT, Tian YL, et al (2018) Representation learning on graphs with jumping knowledge networks. In: International Conference on Machine Learning, pp. 5449–5458
Atwood J, Towsley D (2016) diffusion-convolutional neural networks. In: Neural Information Processing Systems, pp 1993-2001
Min YM, Wenkel F, Wolf G (2020) Scattering GCN: overcoming oversmoothness in graph convolutional networks. In: Neural Information Processing Systems
Xu K, Hu W, Leskovec J, et al (2019) How powerful are graph neural networks. In: International Conference on Learning Representations
Li QM, Han ZC, Wu XM (2018) Deeper insights into graph convolutional networks for semi-supervised learning. In: AAAI Conference on Artificial Intelligence, pp. 3538–3545
Kipf TN (2020) Deep learning with graph-structured representations. University of Amsterdam
Fey M, Lenssen JE (2019) Fast graph representation learning with pytorch geometric. In: International Conference on Learning Representations
Grover A, Leskovec J (2016) Node2vec: scalable feature learning for networks. In: Knowledge Discovery and Data Mining, pp. 855–864
Yang ZL, Cohen W, Salakhudinov R (2016) Revisiting semi-supervised learning with graph embeddings. In: International Conference on Machine Learning, pp. 40–48
Liao RJ, Brockschmidt M, Tarlow D, et al (2018). Graph partition neural networks for semi-supervised classification. In: International Conference on Learning Representations
Yu SW, Yang XB, Zhang WS (2019) PKGCN: prior knowledge enhanced graph convolutional network for graph-based semi-supervised learning. Int J Mach Learn Cybern 10(11):3115–3127
Zhan K, Niu CX (2021) Mutual teaching for graph convolutional networks. Futur Gener Comput Syst 115:837–843
Lei FY, Liu X, Dai QY et al (2020) Hybrid low-order and higher-order graph convolutional networks. Comput Intell Neurosci 3283890:1–9
Chen SB, Tian XZ, Ding CHQ et al (2020) Graph convolutional network based on manifold similarity learning. Cogn Comput 12(6):1144–1153
Acknowledgements
This research is financially supported by the National Key Research and Development Program of China (grant number 2018YFC0807105), National Natural Science Foundation of China (grant number 61462073), and Science and Technology Committee of Shanghai Municipality (STCSM) (under grant numbers 17DZ1101003, 18,511,106,602, and 18DZ2252300).
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
About this article
Cite this article
Wang, J., Guo, Y., Wang, Z. et al. Graph neural network with feature enhancement of isolated marginal groups. Appl Intell 52, 16962–16974 (2022). https://doi.org/10.1007/s10489-022-03277-x
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-022-03277-x