EUVIMEDEUVIMED entdecken
Crossref

DMHANT: DropMessage Hypergraph Attention Network for Information Propagation Prediction

Qi Ouyang, Hongchang Chen, Shuxin Liu iD, Liming Pu, Dongdong Ge, Ke Fan

Big Data · 2024

DOI: 10.1089/big.2023.0131 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Big Data, 2024. Verfasst von Qi Ouyang und 5 weiteren Autor:innen. Beteiligte Einrichtung: People's Liberation Army Strategic Support Force Information Engineering University, Zhengzhou, China. Hauptthemen laut MEDLINE: Information Dissemination, Social Networking. Die Arbeit nennt 33 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Predicting propagation cascades is crucial for understanding information propagation in social networks. Existing methods always focus on structure or order of infected users in a single cascade sequence, ignoring the global dependencies of cascades and users, which is insufficient to characterize their dynamic interaction preferences. Moreover, existing methods are poor at addressing the problem of model robustness. To address these issues, we propose a predication model named DropMessage Hypergraph Attention Networks, which constructs a hypergraph based on the cascade sequence. Specifically, to dynamically obtain user preferences, we divide the diffusion hypergraph into multiple subgraphs according to the time stamps, develop hypergraph attention networks to explicitly learn complete interactions, and adopt a gated fusion strategy to connect them for user cascade prediction. In addition, a new drop immediately method DropMessage is added to increase the robustness of the model. Experimental results on three real-world datasets indicate that proposed model significantly outperforms the most advanced information propagation prediction model in both MAP@k and Hits@K metrics, and the experiment also proves that the model achieves more significant prediction performance than the existing model under data perturbation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Information DisseminationSocial NetworkingAlgorithmsHumans

Stichwörter der Autor:innen

DropMessagecascade predictiondynamic interaction preferenceshypergraph attention networksrobustness

Autor:innen und Institutionen

  • People's Liberation Army Strategic Support Force Information Engineering University, Zhengzhou, China.
  • National Digital Switching System Engineering and Technological R&D Center, Zhengzhou, China.

ORCID-Profile: Shuxin Liu

Zitieren

APA

Ouyang, Q., Chen, H., Liu, S., Pu, L., Ge, D., & Fan, K. (2024). DMHANT: DropMessage Hypergraph Attention Network for Information Propagation Prediction. Big Data. https://doi.org/10.1089/big.2023.0131

Vancouver

Ouyang Q, Chen H, Liu S, Pu L, Ge D, Fan K. DMHANT: DropMessage Hypergraph Attention Network for Information Propagation Prediction. Big Data. 2024. doi:10.1089/big.2023.0131

BibTeX
@article{Ouyang2024,
  author = {Ouyang, Qi and Chen, Hongchang and Liu, Shuxin and Pu, Liming and Ge, Dongdong and Fan, Ke},
  title = {DMHANT: DropMessage Hypergraph Attention Network for Information Propagation Prediction},
  journal = {Big Data},
  year = {2024},
  doi = {10.1089/big.2023.0131}
}
Kostenlos starten →