Performance Validation of Jointly Optimized Graph Filters

Bin Cui

doi:10.54097/7w257b72

Authors

Bin Cui

DOI:

https://doi.org/10.54097/7w257b72

Keywords:

Graph signal processing, graph filters, joint optimization.

Abstract

In this paper, a novel jointly optimized graph filter is investigated, which is based on the vertex sampling method and the sum-of-squares integration method. It takes the frequency response of the ideal graph filter and the error value of the frequency response of the designed graph filter as the optimization objectives of the jointly optimized graph filter. Firstly, the theoretical analysis and validation of the practical performance of this method are carried out in this paper, and theoretically, we can get that the performance of the jointly optimized graph filter is improved compared with that of the non-jointly optimized graph filter. Then, the actual performance of the jointly optimized graph filter is verified using real data sets. Finally, the jointly optimized graph filter design method is compared with two benchmark graph filter design methods. It is concluded that the performance of the jointly optimized graph filter also has a good improvement over the benchmark graph filters.

References

F. Battiston, V. Nicosia, V. Latora, “Structural measures for multiplex networks,” Physical Review E, vol.89, 2014.

M. E. J. Newman,“The structure and function of complex networks,” SIAM review, vol.45,pp. 167-256,2003.

D. Wang, D. Pedreschi, C. Song,“ Human mobility, social ties, and link prediction, ” Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining,pp. 1100-1108,2011.

J. Leskovec, J. Kleinberg, C. Faloutsos, “Graph evolution: Densification and shrinking diameters,” ACM transactions on Knowledge Discovery from Data (TKDD), vol. 1,pp. 2-es,2007.

A. Sandryhaila, J. M. F. Moura,“ Discrete signal processing on graphs,” IEEE transactions on signal processing, vol.61,pp. 1644-1656,2013.

D. I. Shuman, S. K. Narang, P. Frossard, “The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains,” IEEE signal processing magazine, vol. 30, pp. 83-98,2013.

D. K. Hammond, P. Vandergheynst, R. Gribonval, “Wavelets on graphs via spectral graph theory,” Applied and Computational Harmonic Analysis, vol. 30, pp. 129-150,2011.

A. Ortega, P. Frossard, J. Kovačević,“ Graph signal processing: Overview, challenges, and applications,” Proceedings of the IEEE, vol.106,pp. 808-828,2018.

J. Zhou, G. Cui, S. Hu, ,“Graph neural networks: A review of methods and applications,” AI open, vol. 1,pp. 57-81,2020.

Y. Liu, Y. Zhang, W. Wang, et al, “ARMA graph filter design: Two approaches,” IEEE Transactions on Signal Processing, vol. 67, pp. 4050-4063,2019.

S. Tuomas, “Graph Filters: A Design Perspective,” IEEE Signal Processing Magazine, vol.36,pp. 82-101,2019.

S. Yangan, L. Zhang, J. Wang, et al,“ Wiener graph filter in graph spectral domain for image denoising,” Signal Processing: Image Communication,vol. 85, 2020.

B. Cui, and L. Cheng, “The joint optimization method of the graph filter design: the vertex sampling and the integration method,”Fifteenth International Conference on Signal Processing Systems (ICSPS 2023) ,2024.

D. B. Tay, “Sensor network data denoising via recursive graph median filters, ”Signal Process, vol.189,pp. 302,2021.

F .Grassi, A. Loukas, N. Perraudin, “ A time-vertex signal processing framework: scalable processing and meaningful representations for time-series on graphs, ” IEEE Trans,Signal Process, vol.66,pp. 817–829,2018.

K. Qiu, X .Mao, X. Shen,“Time-varying graph signal reconstruction, ”IEEE J. Sel. Top. Signal Process, vol.11,pp. 870–883,2017.