A Comprehensive Investigation on Graph Neural Networks: Models, Applications, and Future Challenges

Xinyang Chen

doi:10.54097/mqt28f71

Authors

Xinyang Chen

DOI:

https://doi.org/10.54097/mqt28f71

Keywords:

Graph Neural Network, machine learning, deep learning.

Abstract

Graphs, as a kind of complex data structure, are getting wide attention these days, requiring more research on relative models to extract information and make predictions based on graphs. Especially, Graph Neural Network (GNN) shows high performance in many areas. This paper surveys both traditional and advanced GNN models, with their core principles and creative features. It also introduces real-life applications of GNN models, including social recommender systems, drug discovery and traffic prediction. Additionally, this paper discusses current bottlenecks of GNN and prospects of possible improvements. By reviewing GNN from different aspects, this paper tries to provide an entire perspective on this direction for readers. People now encounter many more types of graphs than before, ranging from urban road networks to social platforms, and even molecular structures in biology. By connecting these scenarios, this paper emphasizes the growing importance of GNN research and its potential to transform both scientific discovery and industrial applications.

Downloads

Download data is not yet available.

References

[1] Wu Z., Pan S., Chen F., Long G., Zhang C., Yu P. S. A comprehensive survey on graph neural networks. IEEE Transactions on Neural Networks and Learning Systems, 2021, 32 (1): 4-24.

[2] Ma L., et al. Acceleration algorithms in GNNs: A survey. IEEE Transactions on Knowledge and Data Engineering, 2025, 37 (6): 3173-3192.

[3] Kipf T. N., Welling M. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907, 2016.

[4] Hamilton W., Ying Z., Leskovec J. Inductive representation learning on large graphs. Advances in Neural Information Processing Systems, 2017, 30: 1024-1034.

[5] Veličković P., Cucurull G., Casanova A., Romero A., Liò P., Bengio Y. Graph attention networks. arXiv preprint arXiv:1710.10903, 2017.

[6] Xu K., Hu W., Leskovec J., Jegelka S. How powerful are graph neural networks? arXiv preprint arXiv:1810.00826, 2018.

[7] Li Y., Li Z., Wang P., Li J., Sun X., Cheng H., Yu J. X. A survey of graph meets large language model: Progress and future directions. arXiv preprint arXiv:2311.12399, 2023.

[8] Topping J., Di Giovanni F., Chamberlain B. P., Dong X., Bronstein M. M. Understanding over-squashing and bottlenecks on graphs via curvature. arXiv preprint arXiv:2111.14522, 2021.

[9] You Y., Chen T., Sui Y., Chen T., Wang Z., Shen Y. Graph contrastive learning with augmentations. Advances in Neural Information Processing Systems, 2020, 33: 5812-5823.

[10] Hou Z., Liu X., Cen Y., Dong Y., Yang H., Wang C., Tang J. GraphMAE: Self-supervised masked graph autoencoders. Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2022: 594-604.

[11] Hou Z., He Y., Cen Y., Liu X., Dong Y., Kharlamov E., Tang J. GraphMAE2: A decoding-enhanced masked self-supervised graph learner. Proceedings of the ACM Web Conference, 2023: 737-746.

[12] Pfaff T., Fortunato M., Sanchez-Gonzalez A., Battaglia P. Learning mesh-based simulation with graph networks. International Conference on Learning Representations, 2020.

[13] Jumper J., Evans R., Pritzel A., Green T., Figurnov M., Ronneberger O., et al. Highly accurate protein structure prediction with AlphaFold. Nature, 2021, 596 (7873): 583-589.

[14] Brandstetter J., Worrall D., Welling M. Message passing neural PDE solvers. arXiv preprint arXiv:2202.03376, 2022.

[15] Sharma K., Lee Y. C., Nambi S., Salian A., Shah S., Kim S. W., Kumar S. A survey of graph neural networks for social recommender systems. ACM Computing Surveys, 2024, 56 (10): 1-34.

[16] Fan W., Ma Y., Li Q., He Y., Zhao E., Tang J., Yin D. Graph neural networks for social recommendation. Proceedings of the World Wide Web Conference, 2019: 417-426.

[17] Wu Q., Zhang H., Gao X., He P., Weng P., Gao H., Chen G. Dual graph attention networks for deep latent representation of multifaceted social effects in recommender systems. Proceedings of the World Wide Web Conference, 2019: 2091-2102.

[18] Bongini P., Bianchini M., Scarselli F. Molecular generative graph neural networks for drug discovery. Neurocomputing, 2021, 450: 242-252.

[19] Wang X., Ma Y., Wang Y., Jin W., Wang X., Tang J., et al. Traffic flow prediction via spatial temporal graph neural network. Proceedings of the Web Conference, 2020: 1082-1092.

[20] Li F., Feng J., Yan H., Jin G., Yang F., Sun F., et al. Dynamic graph convolutional recurrent network for traffic prediction: Benchmark and solution. ACM Transactions on Knowledge Discovery from Data, 2023, 17 (1): 1-21.

[21] Rusch T. K., Bronstein M. M., Mishra S. A survey on oversmoothing in graph neural networks. arXiv preprint arXiv:2303.10993, 2023.

[22] Topping J., Di Giovanni F., Chamberlain B. P., Dong X., Bronstein M. M. Understanding over-squashing and bottlenecks on graphs via curvature. arXiv preprint arXiv:2111.14522, 2021.