EUVIMEDEUVIMED entdecken
Crossref

Dynamic Spiking Graph Neural Networks

Nan Yin, Mengzhu Wang, Zhenghan Chen, Giulia De Masi, Huan Xiong, Bin Gu

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (15) · 16495-16503

DOI: 10.1609/aaai.v38i15.29587 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Nan Yin und 5 weiteren Autor:innen. Die Arbeit wurde bisher 31-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The integration of Spiking Neural Networks (SNNs) and Graph Neural Networks (GNNs) is gradually attracting attention due to the low power consumption and high efficiency in processing the non-Euclidean data represented by graphs. However, as a common problem, dynamic graph representation learning faces challenges such as high complexity and large memory overheads. Current work often uses SNNs instead of Recurrent Neural Networks (RNNs) by using binary features instead of continuous ones for efficient training, which overlooks graph structure information and leads to the loss of details during propagation. Additionally, optimizing dynamic spiking models typically requires the propagation of information across time steps, which increases memory requirements. To address these challenges, we present a framework named Dynamic Spiking Graph Neural Networks (Dy-SIGN). To mitigate the information loss problem, Dy-SIGN propagates early-layer information directly to the last layer for information compensation. To accommodate the memory requirements, we apply the implicit differentiation on the equilibrium state, which does not rely on the exact reverse of the forward computation. While traditional implicit differentiation methods are usually used for static situations, Dy-SIGN extends it to the dynamic graph setting. Extensive experiments on three large-scale real-world dynamic graph datasets validate the effectiveness of Dy-SIGN on dynamic node classification tasks with lower computational costs.

Zitieren

APA

Yin, N., Wang, M., Chen, Z., Masi, G. D., Xiong, H., & Gu, B. (2024). Dynamic Spiking Graph Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 38(15), 16495-16503. https://doi.org/10.1609/aaai.v38i15.29587

Vancouver

Yin N, Wang M, Chen Z, Masi GD, Xiong H, Gu B. Dynamic Spiking Graph Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(15):16495-16503. doi:10.1609/aaai.v38i15.29587

BibTeX
@article{Yin2024,
  author = {Yin, Nan and Wang, Mengzhu and Chen, Zhenghan and Masi, Giulia De and Xiong, Huan and Gu, Bin},
  title = {Dynamic Spiking Graph Neural Networks},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {15},
  pages = {16495--16503},
  doi = {10.1609/aaai.v38i15.29587}
}
Kostenlos starten →