HyperDet: Source Detection in Hypergraphs via Interactive Relationship Construction and Feature-rich Attention Fusion

Cheng, Le; Zhu, Peican; Guo, Yangming; Tang, Keke; Gao, Chao; Wang, Zhen

doi:10.24963/ijcai.2025/307

HyperDet: Source Detection in Hypergraphs via Interactive Relationship Construction and Feature-rich Attention Fusion

Le Cheng, Peican Zhu, Yangming Guo, Keke Tang, Chao Gao, Zhen Wang

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 2758-2766.

https://doi.org/10.24963/ijcai.2025/307

Keywords

Data Mining: DM: Networks
Data Mining: DM: Mining graphs
Machine Learning: ML: Deep learning architectures
Machine Learning: ML: Convolutional networks

Abstract

Hypergraphs offer superior modeling capabilities for social networks, particularly in capturing group phenomena that extend beyond pairwise interactions in rumor propagation. Existing approaches in rumor source detection predominantly focus on dyadic interactions, which inadequately address the complexity of more intricate relational structures. In this study, we present a novel approach for Source Detection in Hypergraphs (HyperDet) via Interactive Relationship Construction and Feature-rich Attention Fusion. Specifically, our methodology employs an Interactive Relationship Construction module to accurately model both the static topology and dynamic interactions among users, followed by the Feature-rich Attention Fusion module, which autonomously learns node features and discriminates between nodes using a self-attention mechanism, thereby effectively learning node representations under the framework of accurately modeled higher-order relationships. Extensive experimental validation confirms the efficacy of our HyperDet approach, showcasing its superiority relative to current state-of-the-art methods.

Le Cheng, Peican Zhu, Yangming Guo, Keke Tang, Chao Gao, and Zhen Wang. 2025. HyperDet: Source Detection in Hypergraphs via Interactive Relationship Construction and Feature-rich Attention Fusion. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 2758–2766. https://doi.org/10.24963/ijcai.2025/307

@inproceedings{ijcai2025p307,
  title     = {HyperDet: Source Detection in Hypergraphs via Interactive Relationship Construction and Feature-rich Attention Fusion},
  author    = {Cheng, Le and Zhu, Peican and Guo, Yangming and Tang, Keke and Gao, Chao and Wang, Zhen},
  booktitle = {Proceedings of the Thirty-Fourth International Joint Conference on
               Artificial Intelligence, {IJCAI-25}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {James Kwok},
  pages     = {2758--2766},
  year      = {2025},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2025/307},
  url       = {https://doi.org/10.24963/ijcai.2025/307},
}

TY  - CPAPER
TI  - HyperDet: Source Detection in Hypergraphs via Interactive Relationship Construction and Feature-rich Attention Fusion
AU  - Cheng, Le
AU  - Zhu, Peican
AU  - Guo, Yangming
AU  - Tang, Keke
AU  - Gao, Chao
AU  - Wang, Zhen
T2  - Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2025
SP  - 2758
EP  - 2766
DO  - 10.24963/ijcai.2025/307
UR  - https://doi.org/10.24963/ijcai.2025/307
ER  -