WaveNet: Tackling Non-stationary Graph Signals via Graph Spectral Wavelets
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (8) · 9287-9295
DOI: 10.1609/aaai.v38i8.28781 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Zhirui Yang und 8 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref).
Abstract (Originalsprache)
In the existing spectral GNNs, polynomial-based methods occupy the mainstream in designing a filter through the Laplacian matrix. However, polynomial combinations factored by the Laplacian matrix naturally have limitations in message passing (e.g., over-smoothing). Furthermore, most existing spectral GNNs are based on polynomial bases, which struggle to capture the high-frequency parts of the graph spectral signal. Additionally, we also find that even increasing the polynomial order does not change this situation, which means polynomial-based models have a natural deficiency when facing high-frequency signals. To tackle these problems, we propose WaveNet, which aims to effectively capture the high-frequency part of the graph spectral signal from the perspective of wavelet bases through reconstructing the message propagation matrix. We utilize Multi-Resolution Analysis (MRA) to model this question, and our proposed method can reconstruct arbitrary filters theoretically. We also conduct node classification experiments on real-world graph benchmarks and achieve superior performance on most datasets. Our code is available at https://github.com/Bufordyang/WaveNet
Zitieren
APA
Yang, Z., Hu, Y., Ouyang, S., Liu, J., Wang, S., Ma, X., Wang, W., Su, H., & Liu, Y. (2024). WaveNet: Tackling Non-stationary Graph Signals via Graph Spectral Wavelets. Proceedings of the AAAI Conference on Artificial Intelligence, 38(8), 9287-9295. https://doi.org/10.1609/aaai.v38i8.28781
Vancouver
Yang Z, Hu Y, Ouyang S, Liu J, Wang S, Ma X, et al. WaveNet: Tackling Non-stationary Graph Signals via Graph Spectral Wavelets. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(8):9287-9295. doi:10.1609/aaai.v38i8.28781
BibTeX
@article{Yang2024,
author = {Yang, Zhirui and Hu, Yulan and Ouyang, Sheng and Liu, Jingyu and Wang, Shuqiang and Ma, Xibo and Wang, Wenhan and Su, Hanjing and Liu, Yong},
title = {WaveNet: Tackling Non-stationary Graph Signals via Graph Spectral Wavelets},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {8},
pages = {9287--9295},
doi = {10.1609/aaai.v38i8.28781}
}
EUVIMED