Deep Learning and Graph Neural Networks for Mathematical Pattern Recognition: Techniques, Challenges, and Advances

Lipika Mishra; Garima  Singh; Anshu Singh

doi:10.69968/ijisem.2025v4i2313-319

Authors

Lipika Mishra Dept. of Mathematics, Barkatullah University, Bhopal (M.P.), India https://orcid.org/0009-0007-5361-5999
Garima Singh Dept. of Mathematics, Barkatullah University, Bhopal (M.P.), India https://orcid.org/0009-0009-5502-5006
Anshu Singh Dept. of Mathematics, Barkatullah University, Bhopal (M.P.), India https://orcid.org/0009-0009-5502-5006

DOI:

https://doi.org/10.69968/ijisem.2025v4i2313-319

Keywords:

Deep Learning, Graph Neural Networks, Mathematical, Pattern Recognition, Machine Learning, Artificial Intelligent

Abstract

Complex systems are often modelled using graphs, and one of the key tasks in complex system analysis is identifying anomalies in a graph. A graph anomaly is a pattern that does not follow the typical patterns predicted by the graph's structures and/or properties. The present article provides a comprehensive review of the techniques, challenges, and advancements in the field of Deep Learning and Graph Neural Networks for Mathematical Pattern Recognition. This review highlights the effectiveness of Deep Learning (DL) and Graph Neural Networks (GNNs) in mathematical pattern recognition. Graph-based models, particularly GraphMR built on Graph2Seq, demonstrate superior performance in model accuracy and efficiency over traditional Seq2Seq methods. GNNs effectively handle structured data like ASTs and DAGs, preserving semantic and syntactic information. The integration of encoder–decoder architectures and graph-based reasoning shows significant advancements in recognizing mathematical structures. The evolution from structural methods to DL and GNN approaches underscores the progress in recognition accuracy. As ML adoption grows, the need for large, high-quality datasets becomes critical for training next-generation models.

Author Biographies

Lipika Mishra, Dept. of Mathematics, Barkatullah University, Bhopal (M.P.), India

Lipika Mishra earned her B.Sc. B.Ed (Mathematics) From Avdhesh Pratap Singh University, Rewa, Madhya Pradesh, India, In 2023 And is currently in final year of M.Sc. Mathematics from Barkatullah University Institute of Technology, BU, Bhopal, Madhya Pradesh, India. She is Proficient in various programming Languages c and c++. Her Main area of Interest in research is the use of Mathematical concepts in solving actual problems existing.
Garima Singh, Dept. of Mathematics, Barkatullah University, Bhopal (M.P.), India

Garima Singh did her graduation in Mathematics (Hons.) & post-graduation from Miranda House College of Delhi University, Delhi. Thereafter she did Ph.D.in Mathematics from Barkatullah University, Bhopal. She is presently working as HOD Mathematics inDepartment of Mathematics UIT Barkatullah University, Bhopal. Her many research papers have been published in national, international and SCI journals. She has guided more than 25 research scholars at Barkatullah University. She has the knowledge of programming languages like-MATLAB, Fortran, Pascal, C, C++. Her fields of specialization include Block Designs, Graph Theory & Mathematical Modelling.
Anshu Singh, Dept. of Mathematics, Barkatullah University, Bhopal (M.P.), India

Anshu Singh Dr. Anshu Singh did her B.Sc. and M.Sc in Mathematics from Barkartullah University Bhopal. She did her PhD. in Mathematics from MP Bhoj open university on Regular mode. she is presently working as Asst. Prof. in Dept. of Mathematics UIT, Barkatullah University Bhopal. She has a vast experience in academic, administration and researchfield. She has total 33 years of college teaching and research experience 16 years.

References

[1] G. Renton, M. Balcilar, P. Héroux, B. Gaüzère, P. Honeine, and S. Adam, “Symbols Detection and Classification using Graph Neural Networks,” Pattern Recognit. Lett., vol. 152, pp. 391–397, 2021, doi: 10.1016/j.patrec.2021.09.020.

[2] R. Fioresi and F. Zanchetta, “Deep learning and geometric deep learning: An introduction for mathematicians and physicists,” Int. J. Geom. Methods Mod. Phys., vol. 20, no. 12, pp. 1–49, 2023, doi: 10.1142/S0219887823300064.

[3] S. Xiao, J. Li, J. Lu, S. Huang, B. Zeng, and S. Wang, “Graph neural networks for multi-view learning: a taxonomic review,” Artif. Intell. Rev., vol. 57, no. 12, 2024, doi: 10.1007/s10462-024-10990-1.

[4] X. M. Zhang, L. Liang, L. Liu, and M. J. Tang, “Graph Neural Networks and Their Current Applications in Bioinformatics,” Front. Genet., vol. 12, no. July, pp. 1–22, 2021, doi: 10.3389/fgene.2021.690049.

[5] W. Jiang et al., “Graph Neural Networks for Routing Optimization: Challenges and Opportunities,” Sustain., vol. 16, no. 21, pp. 1–34, 2024, doi: 10.3390/su16219239.

[6] P. Reiser et al., “Graph neural networks for materials science and chemistry,” Commun. Mater., vol. 3, no. 1, pp. 1–18, 2022, doi: 10.1038/s43246-022-00315-6.

[7] A. M. B. da Silva, N. C. da S. Ferreira, L. A. M. Braga, F. B. Mota, V. Maricato, and L. A. Alves, “Graph Neural Networks: A Bibliometric Mapping of the Research Landscape and Applications,” Inf., vol. 15, no. 10, 2024, doi: 10.3390/info15100626.

[8] K. Choudhary et al., “Recent advances and applications of deep learning methods in materials science,” NOJ Comput. Mater., vol. 59, 2022, doi: 10.1038/s41524-022-00734-6.

[9] U. A. Bhatti, H. Tang, G. Wu, S. Marjan, and A. Hussain, “Deep Learning with Graph Convolutional Networks: An Overview and Latest Applications in Computational Intelligence,” Int. J. Intell. Syst., 2023, doi: 10.1155/2023/8342104.

[10] P. Dixit and P. B. Singh, “The Impact of Artificial Intelligence on Various Sectors: Benefits, Challenges, and Future Prospects,” Interantional J. Sci. Res. Eng. Manag., vol. 08, no. 04, pp. 1–5, 2024, doi: 10.55041/ijsrem30655.

[11] J. Gao and L. Hao, “Graph Neural Network and its applications,” J. Phys. Conf. Ser., vol. 1994, no. 1, 2021, doi: 10.1088/1742-6596/1994/1/012004.

[12] B. Khemani, S. Patil, K. Kotecha, and S. Tanwar, “A review of graph neural networks: concepts, architectures, techniques, challenges, datasets, applications, and future directions,” J. Big Data, vol. 11, no. 1, 2024, doi: 10.1186/s40537-023-00876-4.

[13] A. Gupta, P. Matta, and B. Pant, “Graph neural network: Current state of Art, challenges and applications,” Mater. Today Proc., 2021, doi: 10.1016/j.matpr.2021.01.950.

[14] H. Kim, B. S. Lee, W. Y. Shin, and S. Lim, “Graph Anomaly Detection With Graph Neural Networks: Current Status and Challenges,” IEEE Access, vol. 10, 2022, doi: 10.1109/ACCESS.2022.3211306.

[15] Z. Jia et al., “Recent Research Progress of Graph Neural Networks in Computer Vision,” Electron., vol. 14, no. 9, 2025, doi: 10.3390/electronics14091742.

[16] T. N. Truong, C. T. Nguyen, R. Zanibbi, H. Mouchère, and M. Nakagawa, “A survey on handwritten mathematical expression recognition: The rise of encoder-decoder and GNN models,” Pattern Recognit., 2024, doi: 10.1016/j.patcog.2024.110531.

[17] J. Serey et al., “Pattern Recognition and Deep Learning Technologies, Enablers of Industry 4.0, and Their Role in Engineering Research,” Symmetry (Basel)., vol. 15, no. 2, 2023, doi: 10.3390/sym15020535.

[18] A. Keramatfar, M. Rafiee, and H. Amirkhani, “Graph Neural Networks: A bibliometrics overview,” Mach. Learn. with Appl., vol. 10, no. August, p. 100401, 2022, doi: 10.1016/j.mlwa.2022.100401.

[19] N. Lad, “Graph Neural Networks for Pattern Recognition and Fast Track Finding,” Proc. CTD, 2022.

[20] W. Feng, B. Liu, D. Xu, Q. Zheng, and Y. Xu, “GraphMR: Graph Neural Network for Mathematical Reasoning,” Conf. Empir. Methods Nat. Lang. Process., no. 2018, pp. 3395–3404, 2021, doi: 10.18653/v1/2021.emnlp-main.273.