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

TL;DR

HyperDet introduces a novel hypergraph-based method for rumor source detection that models complex relationships and employs attention mechanisms, outperforming existing dyadic interaction-focused approaches.

Contribution

The paper proposes HyperDet, a new hypergraph-based framework that captures higher-order relationships and uses feature-rich attention fusion for improved source detection.

Findings

HyperDet outperforms state-of-the-art methods in rumor source detection.

The approach effectively models static and dynamic user interactions.

Attention mechanisms enhance node feature learning.

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.