SourceDetMamba: A Graph-aware State Space Model for Source Detection in Sequential Hypergraphs

2025-05-19

AI Summary

To address the limited capability of existing methods in modeling higher-order and temporal dynamics for rumor source detection in social networks, this paper proposes the first sequence-based hypergraph learning framework for rumor source identification. Methodologically: (1) it constructs a temporal hypergraph model to capture higher-order group interactions; (2) it employs reverse-order propagation snapshots as input to explicitly invert the rumor diffusion dynamics; and (3) it introduces the Mamba state-space model—the first such adoption in hypergraph learning—augmented with a graph-aware state update mechanism that jointly encodes temporal dependencies and hypergraph topology. Evaluated on eight real-world datasets, the proposed method consistently outperforms state-of-the-art approaches, achieving significant improvements in source node localization accuracy. Experimental results validate both the effectiveness and generalizability of temporal inverse modeling and state-space modeling for hypergraph-based rumor溯源.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Content-based information diffusion

Abstract

Source detection on graphs has demonstrated high efficacy in identifying rumor origins. Despite advances in machine learning-based methods, many fail to capture intrinsic dynamics of rumor propagation. In this work, we present SourceDetMamba: A Graph-aware State Space Model for Source Detection in Sequential Hypergraphs, which harnesses the recent success of the state space model Mamba, known for its superior global modeling capabilities and computational efficiency, to address this challenge. Specifically, we first employ hypergraphs to model high-order interactions within social networks. Subsequently, temporal network snapshots generated during the propagation process are sequentially fed in reverse order into Mamba to infer underlying propagation dynamics. Finally, to empower the sequential model to effectively capture propagation patterns while integrating structural information, we propose a novel graph-aware state update mechanism, wherein the state of each node is propagated and refined by both temporal dependencies and topological context. Extensive evaluations on eight datasets demonstrate that SourceDetMamba consistently outperforms state-of-the-art approaches.

Problem

• Detect rumor sources in sequential hypergraphs effectively
• Model high-order social interactions using hypergraphs
• Integrate temporal and structural data for propagation dynamics

Innovation

• Uses hypergraphs for high-order social interactions
• Employs Mamba for global propagation dynamics
• Integrates graph-aware state update mechanism