CasODE: Modeling Irregular Information Cascade via Neural Ordinary Differential Equations (Student Abstract)

Zhangtao Cheng, Xovee Xu, Ting Zhong, Fan Zhou, Goce Trajcevski

AAAI 2023 pp. 16192-16193

doi:10.1609/AAAI.V37I13.26956 /aaai/2023/cheng2023aaai-casode/

Abstract

Predicting information cascade popularity is a fundamental problem for understanding the nature of information propagation on social media. However, existing works fail to capture an essential aspect of information propagation: the temporal irregularity of cascade event -- i.e., users' re-tweetings at random and non-periodic time instants. In this work, we present a novel framework CasODE for information cascade prediction with neural ordinary differential equations (ODEs). CasODE generalizes the discrete state transitions in RNNs to continuous-time dynamics for modeling the irregular-sampled events in information cascades. Experimental evaluations on real-world datasets demonstrate the advantages of the CasODE over baseline approaches.

PDF AAAI Semantic Scholar

Cite

Text

Cheng et al. "CasODE: Modeling Irregular Information Cascade via Neural Ordinary Differential Equations (Student Abstract)." AAAI Conference on Artificial Intelligence, 2023. doi:10.1609/AAAI.V37I13.26956

Markdown

[Cheng et al. "CasODE: Modeling Irregular Information Cascade via Neural Ordinary Differential Equations (Student Abstract)." AAAI Conference on Artificial Intelligence, 2023.](https://mlanthology.org/aaai/2023/cheng2023aaai-casode/) doi:10.1609/AAAI.V37I13.26956

BibTeX

@inproceedings{cheng2023aaai-casode,
  title     = {{CasODE: Modeling Irregular Information Cascade via Neural Ordinary Differential Equations (Student Abstract)}},
  author    = {Cheng, Zhangtao and Xu, Xovee and Zhong, Ting and Zhou, Fan and Trajcevski, Goce},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2023},
  pages     = {16192-16193},
  doi       = {10.1609/AAAI.V37I13.26956},
  url       = {https://mlanthology.org/aaai/2023/cheng2023aaai-casode/}
}