HIP: Model-Agnostic Hypergraph Influence Prediction via Distance-Centrality Fusion and Neural ODEs

2025-08-21

AI Summary

Predicting user influence in hypergraphs is challenging due to the absence of explicit propagation trajectories (e.g., cascades or infection paths). Method: We propose HIP, a model-agnostic, unified framework that (i) fuses multi-dimensional centrality measures with a reconstructed distance matrix to characterize higher-order diffusion capacity; (ii) employs a multi-hop hypergraph neural network (HNN) to extract structural features; and (iii) jointly models temporal dynamics via coupled LSTM and neural ordinary differential equations (Neural ODEs). HIP is modular, scalable, and requires no prior assumptions about underlying propagation models. Contribution/Results: Evaluated on 14 real-world hypergraph datasets, HIP significantly outperforms state-of-the-art methods in prediction accuracy, robustness, and top-influencer identification—establishing a new unsupervised paradigm for hypergraph influence prediction.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Content-based information diffusion

Abstract

Predicting user influence in social networks is a critical problem, and hypergraphs, as a prevalent higher-order modeling approach, provide new perspectives for this task. However, the absence of explicit cascade or infection probability data makes it particularly challenging to infer influence in hypergraphs. To address this, we introduce HIP, a unified and model-independent framework for influence prediction without knowing the underlying spreading model. HIP fuses multi-dimensional centrality indicators with a temporally reinterpreted distance matrix to effectively represent node-level diffusion capacity in the absence of observable spreading. These representations are further processed through a multi-hop Hypergraph Neural Network (HNN) to capture complex higher-order structural dependencies, while temporal correlations are modeled using a hybrid module that combines Long Short-Term Memory (LSTM) networks and Neural Ordinary Differential Equations (Neural ODEs). Notably, HIP is inherently modular: substituting the standard HGNN with the advanced DPHGNN, and the LSTM with xLSTM, yields similarly strong performance, showcasing its architectural generality and robustness. Empirical evaluations across 14 real-world hypergraph datasets demonstrate that HIP consistently surpasses existing baselines in prediction accuracy, resilience, and identification of top influencers, all without relying on any diffusion trajectories or prior knowledge of the spreading model. These findings underline HIP's effectiveness and adaptability as a general-purpose solution for influence prediction in complex hypergraph environments.

Problem

• Predicting user influence in hypergraphs without cascade data
• Inferring node-level diffusion capacity without spreading models
• Modeling higher-order dependencies without diffusion trajectories

Innovation

• Fuses centrality and distance for diffusion representation
• Uses multi-hop Hypergraph Neural Network for dependencies
• Combines LSTM and Neural ODEs for temporal modeling