Hypergraph source detection improved by causal disentanglement method
HyperCD: Effective Source Detection in Hypergraphs via Causal Disentanglement
Social and Information Networks
Summary
When harmful rumors spread through complex networks where multiple people interact at once, it can be hard to find who started them. The authors designed a new way to detect the source in these networks (called hypergraphs) by separating the true cause of the spread from unrelated noise in the data. Their method uses clever math tools to separate these signals and better focus on the real source of information flow. Tests on several datasets show it works better than existing techniques.
What this means in practice
- •For social media analysts: Identify the origin of harmful rumors spreading across group interactions in social media platforms more accurately using causal disentanglement.
- •For public health officials: Track the initial source of misinformation spreading through complex community networks to improve intervention strategies.
Authors
Yan Kang, Peican Zhu, Keke Tang, Le Cheng, Zun Liu, Ang Dong, Yangming Guo
Abstract
Source detection in hypergraphs plays an important role in mitigating the spread of harmful rumors and ensuring social stability. Current methods frequently overlook the causal entanglement problem in observations, thereby limiting the performance of source inference. In this work, we propose a source detection approach in Hypergraphs via Causal Disentanglement (HyperCD). To decouple causal propagation semantics from confounding noise, we propose the causal disentanglement module. A dual-branch variational encoder is utilized to disentangle snapshot embeddings into causal and confounding latent spaces, ensuring that the inference module relies solely on causal propagation signals. To further enforce this separation, an adversarial inference loss term is introduced to guarantee statistical independence between the decoupled branches. Moreover, to capture diffusion dynamics in hypergraphs, an attention-based hypergraph aggregation module is designed, which comprises the node-to-hyperedge propagation and hyperedge-to-node propagation processes. Extensive experiments on six datasets demonstrate the superiority of our HyperCD in effectively mitigating the causal entanglement problem.