Community Aware Temporal Network Generation

2025-01-13

AI Summary

Existing social network generation methods fail to accurately capture the dynamic evolution of real-world communities, leading to distortions in synthetic temporal networks—particularly under constraints of temporal span, scale, and privacy. This paper proposes the first generative framework that explicitly couples node-level community label evolution with dynamic interaction modeling. Our approach achieves faithful synthesis of cross-community interaction patterns via community-aware temporal edge sampling and structural metric-driven optimization. Built upon a scalable network generation architecture, it supports high-fidelity synthesis of large-scale, long-duration temporal networks. Extensive evaluation on multiple real-world face-to-face interaction datasets demonstrates that our method significantly outperforms baselines across key metrics—including degree distribution, clustering coefficient, community lifetime, and evolutionary trajectory—thereby alleviating critical bottlenecks such as data scarcity, privacy sensitivity, and high acquisition costs.

Technology Category

• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Natural Language Processing: Generation
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Web Mining and Content Analysis: Web data generation and simulation

Abstract

The advantages of temporal networks in capturing complex dynamics, such as diffusion and contagion, has led to breakthroughs in real world systems across numerous fields. In the case of human behavior, face-to-face interaction networks enable us to understand the dynamics of how communities emerge and evolve in time through the interactions, which is crucial in fields like epidemics, sociological studies and urban science. However, state-of-the-art datasets suffer from a number of drawbacks, such as short time-span for data collection and a small number of participants. Moreover, concerns arise for the participants' privacy and the data collection costs. Over the past years, many successful algorithms for static networks generation have been proposed, but they often do not tackle the social structure of interactions or their temporal aspect. In this work, we extend a recent network generation approach to capture the evolution of interactions between different communities. Our method labels nodes based on their community affiliation and constructs surrogate networks that reflect the interactions of the original temporal networks between nodes with different labels. This enables the generation of synthetic networks that replicate realistic behaviors. We validate our approach by comparing structural measures between the original and generated networks across multiple face-to-face interaction datasets.

Problem

• Dynamic Social Networks
• Community Evolution
• Temporal Network Simulation

Innovation

• Dynamic Community Modeling
• Realistic Temporal Networks
• Face-to-Face Interaction Validation