Signed Graph Neural Ordinary Differential Equation for Modeling Continuous-Time Dynamics
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (8) · 8292-8301
DOI: 10.1609/aaai.v38i8.28670 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Lanlan Chen und 3 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref).
Abstract (Originalsprache)
Modeling continuous-time dynamics constitutes a foundational challenge, and uncovering inter-component correlations within complex systems holds promise for enhancing the efficacy of dynamic modeling. The prevailing approach of integrating graph neural networks with ordinary differential equations has demonstrated promising performance. However, they disregard the crucial signed information potential on graphs, impeding their capacity to accurately capture real-world phenomena and leading to subpar outcomes. In response, we introduce a novel approach: a signed graph neural ordinary differential equation, adeptly addressing the limitations of miscapturing signed information. Our proposed solution boasts both flexibility and efficiency. To substantiate its effectiveness, we seamlessly integrate our devised strategies into three preeminent graph-based dynamic modeling frameworks: graph neural ordinary differential equations, graph neural controlled differential equations, and graph recurrent neural networks. Rigorous assessments encompass three intricate dynamic scenarios from physics and biology, as well as scrutiny across four authentic real-world traffic datasets. Remarkably outperforming the trio of baselines, empirical results underscore the substantial performance enhancements facilitated by our proposed approach. Our code can be found at https://github.com/beautyonce/SGODE.
Zitieren
APA
Chen, L., Wu, K., Lou, J., & Liu, J. (2024). Signed Graph Neural Ordinary Differential Equation for Modeling Continuous-Time Dynamics. Proceedings of the AAAI Conference on Artificial Intelligence, 38(8), 8292-8301. https://doi.org/10.1609/aaai.v38i8.28670
Vancouver
Chen L, Wu K, Lou J, Liu J. Signed Graph Neural Ordinary Differential Equation for Modeling Continuous-Time Dynamics. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(8):8292-8301. doi:10.1609/aaai.v38i8.28670
BibTeX
@article{Chen2024,
author = {Chen, Lanlan and Wu, Kai and Lou, Jian and Liu, Jing},
title = {Signed Graph Neural Ordinary Differential Equation for Modeling Continuous-Time Dynamics},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {8},
pages = {8292--8301},
doi = {10.1609/aaai.v38i8.28670}
}
EUVIMED