Hybrid Graph Signal Processing Deep Learning Framework for Adaptive Network Topology Optimization
Journal of Computer and Communication Networks
Received On : 26 October 2025
Revised On : 02 January 2026
Accepted On : 26 January 2026
Published On : 30 January 2026
Volume 02, 2026
Pages : 013-024
Abstract
The optimization of adaptive network topology is one of the significant problems in the contemporary communication systems because network conditions are dynamic, scale is growing, and data patterns are heterogeneous. This article suggests a new Hybrid Graph Signal Processing-Deep Learning (HGSP-DL) architecture of efficient and intelligent topology optimization in complex network settings. The proposed model is a combination of the structural benefit of graph signal processing and the representation learning ability of deep neural networks to attain strong and scalable performance. The network is first represented as a graph, and the features of nodes are calculated together with the connections to provide smoothness in the spectral analysis of the network, based on the normalized graph Laplacian. A trainable spectral filtering method is used to obtain structure-sensitive embeddings, whereas a deep learning encoder learns non-linear correlations between network nodes. These complementary representations are merged to create a single embedding, which is also used to adaptively optimize network topology by an optimization process that is data-driven. The framework uses an iterative feedback process in order to optimize the connectivity pattern and enhance convergence. Ample simulations have shown that the proposed HGSP-DL model has made great gains in accuracy, packet delivery ratio, and energy savings as well as minimizing latency and convergence time in contrast to current approaches. This model is also highly scaled and can withstand dynamic network conditions such as node mobility and node failures. The findings confirm the suitability of the proposed solution as a dependable solution towards intelligent communication networks of the next generation.
Keywords
Graph Signal Processing, Deep Learning, Network Topology Optimization, Adaptive Networks, Spectral Filtering, Intelligent Communication Systems.
- Y. Yan, E. E. Kuruoglu, and M. A. Altinkaya, “Adaptive sign algorithm for graph signal processing,” Signal Processing, vol. 200, p. 108662, Nov. 2022, doi: 10.1016/j.sigpro.2022.108662.
- A. Jenkins, T. Variddhisai, A. El-Medany, F. S. Ng, and D. Mandic, “Online Graph Topology Learning via Time-Vertex Adaptive Filters: From Theory to Cardiac Fibrillation,” IEEE Transactions on Signal and Information Processing over Networks, vol. 11, pp. 965–979, 2025, doi: 10.1109/tsipn.2025.3594003.
- D. Fu, T. Lu, and J. Wang, “Multi-graph learning with adaptive graph-bag mapping,” Neural Networks, vol. 195, p. 108316, Mar. 2026, doi: 10.1016/j.neunet.2025.108316.
- B. Wang, B. Cai, J. Sheng, and W. Jiao, “AAGCN: a graph convolutional neural network with adaptive feature and topology learning,” Scientific Reports, vol. 14, no. 1, May 2024, doi: 10.1038/s41598-024-60598-2.
- L. Marinucci, C. Battiloro, and P. D. Lorenzo, “Topological Adaptive Least Mean Squares Algorithms Over Simplicial Complexes,” IEEE Transactions on Signal and Information Processing over Networks, vol. 12, pp. 283–298, 2026, doi: 10.1109/tsipn.2026.3663971.
- G. Leus, A. G. Marques, J. M. F. Moura, A. Ortega, and D. I. Shuman, “Graph Signal Processing: History, development, impact, and outlook,” IEEE Signal Processing Magazine, vol. 40, no. 4, pp. 49–60, Jun. 2023, doi: 10.1109/msp.2023.3262906.
- E. Isufi, F. Gama, D. I. Shuman, and S. Segarra, “Graph Filters for Signal Processing and Machine Learning on Graphs,” IEEE Transactions on Signal Processing, vol. 72, pp. 4745–4781, 2024, doi: 10.1109/tsp.2024.3349788.
- Z. Chen et al., “SiamBAN: Target-Aware Tracking With Siamese Box Adaptive Network,” IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 1–17, 2022, doi: 10.1109/tpami.2022.3195759.
- Z. Zhang et al., “Strong and Tough Supramolecular Covalent Adaptable Networks with Room‐Temperature Closed‐Loop Recyclability,” Advanced Materials, vol. 35, no. 7, Dec. 2022, doi: 10.1002/adma.202208619.
- X. Xie, W. Chen, and Z. Kang, “Robust graph structure learning under heterophily,” Neural Networks, vol. 185, p. 107206, May 2025, doi: 10.1016/j.neunet.2025.107206.
- M. Hou et al., “Parallel multi-scale dynamic graph neural network for multivariate time series forecasting,” Pattern Recognition, vol. 158, p. 111037, Feb. 2025, doi: 10.1016/j.patcog.2024.111037.
- D. Zhang and C. Zhu, “A dual path graph neural network framework for dementia diagnosis,” Scientific Reports, vol. 15, no. 1, Jul. 2025, doi: 10.1038/s41598-025-06519-3.
- K. Zhang et al., “A Survey of Deep Graph Learning under Distribution Shifts: From Graph Out-of-Distribution Generalization to Adaptation,” ACM Transactions on Knowledge Discovery from Data, vol. 20, no. 2, pp. 1–38, Feb. 2026, doi: 10.1145/3785475.
- Q. Dai, X.-M. Wu, J. Xiao, X. Shen, and D. Wang, “Graph Transfer Learning via Adversarial Domain Adaptation with Graph Convolution,” IEEE Transactions on Knowledge and Data Engineering, pp. 1–1, 2022, doi: 10.1109/tkde.2022.3144250.
- L. Hu, L. Wei, and Y. Lin, “Decomposition dynamic multi-graph convolutional recurrent network for traffic forecasting,” Applied Intelligence, vol. 55, no. 7, Mar. 2025, doi: 10.1007/s10489-025-06503-4.
- Y. Fang et al., “A Deep‐Learning‐Assisted On‐Mask Sensor Network for Adaptive Respiratory Monitoring,” Advanced Materials, vol. 34, no. 24, May 2022, doi: 10.1002/adma.202200252.
CRediT Author Statement
The authors confirm contribution to the paper as follows:
Conceptualization: John Huria Nderitu and Matt Bowden; Methodology: Matt Bowden; Software: John Huria Nderitu; Data Curation: John Huria Nderitu; Writing- Original Draft Preparation: Matt Bowden; Visualization: John Huria Nderitu and Matt Bowden; Investigation: John Huria Nderitu; Supervision: Matt Bowden; Validation: John Huria Nderitu and Matt Bowden; Writing- Reviewing and Editing: John Huria Nderitu and Matt Bowden. The author reviewed the results and approved the final version of the manuscript.
Acknowledgements
The authors would like to thank to the reviewers for nice comments on the manuscript.
Funding
No funding was received to assist with the preparation of this manuscript.
Ethics Declarations
Conflict of interest
The authors have no conflicts of interest to declare that are relevant to the content of this article.
Availability of Data and Materials
Data sharing is not applicable to this article as no new data were created or analysed in this study.
Author Information
Contributions
All authors have equal contribution in the paper and all authors have read and agreed to the published version of the manuscript.
Corresponding Author
Rights and permissions
This is an open access article distributed under the terms of the Creative Commons Attribution 4.0 International License (CC BY 4.0).
https://creativecommons.org/licenses/by/4.0/.
This license permits unrestricted use, sharing, distribution, reproduction, and adaptation in any medium or format, including for commercial purposes, provided that appropriate credit is given to the original author(s) and the source, a link to the license is provided, and any changes made are indicated.
Copyright
© 2026 John Huria Nderitu and Matt Bowden. The author(s) retain copyright of the work. The author(s) grant the Journal of Computer and Communication Networks (JCCN) and its publisher, Ansis Publications, the right of first publication and the right to identify itself as the original publisher of the article.
Cite this Article
John Huria Nderitu and Matt Bowden, “Hybrid Graph Signal Processing Deep Learning Framework for Adaptive Network Topology Optimization”, Journal of Computer and Communication Networks, pp. 013-024, 2026, doi: 10.64026/JCCN/2026002.