Scaling Up Dynamic Graph Representation Learning via Spiking Neural Networks
Proceedings of the AAAI Conference on Artificial Intelligence · 26.06.2023 · 37 (7) · 8588-8596
DOI: 10.1609/aaai.v37i7.26034 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 26.06.2023. Verfasst von Jintang Li und 8 weiteren Autor:innen. Die Arbeit wurde bisher 37-mal zitiert (Crossref).
Abstract (Originalsprache)
Recent years have seen a surge in research on dynamic graph representation learning, which aims to model temporal graphs that are dynamic and evolving constantly over time. However, current work typically models graph dynamics with recurrent neural networks (RNNs), making them suffer seriously from computation and memory overheads on large temporal graphs. So far, scalability of dynamic graph representation learning on large temporal graphs remains one of the major challenges. In this paper, we present a scalable framework, namely SpikeNet, to efficiently capture the temporal and structural patterns of temporal graphs. We explore a new direction in that we can capture the evolving dynamics of temporal graphs with spiking neural networks (SNNs) instead of RNNs. As a low-power alternative to RNNs, SNNs explicitly model graph dynamics as spike trains of neuron populations and enable spike-based propagation in an efficient way. Experiments on three large real-world temporal graph datasets demonstrate that SpikeNet outperforms strong baselines on the temporal node classification task with lower computational costs. Particularly, SpikeNet generalizes to a large temporal graph (2.7M nodes and 13.9M edges) with significantly fewer parameters and computation overheads.
Zitieren
APA
Li, J., Yu, Z., Zhu, Z., Chen, L., Yu, Q., Zheng, Z., Tian, S., Wu, R., & Meng, C. (2023). Scaling Up Dynamic Graph Representation Learning via Spiking Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 37(7), 8588-8596. https://doi.org/10.1609/aaai.v37i7.26034
Vancouver
Li J, Yu Z, Zhu Z, Chen L, Yu Q, Zheng Z, et al. Scaling Up Dynamic Graph Representation Learning via Spiking Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence. 2023;37(7):8588-8596. doi:10.1609/aaai.v37i7.26034
BibTeX
@article{Li2023,
author = {Li, Jintang and Yu, Zhouxin and Zhu, Zulun and Chen, Liang and Yu, Qi and Zheng, Zibin and Tian, Sheng and Wu, Ruofan and Meng, Changhua},
title = {Scaling Up Dynamic Graph Representation Learning via Spiking Neural Networks},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2023},
volume = {37},
number = {7},
pages = {8588--8596},
doi = {10.1609/aaai.v37i7.26034}
}
EUVIMED