A two-stage model leveraging friendship network for community evolution prediction in interactive networks

2025-03-20

AI Summary

Existing approaches to community evolution prediction in dynamic interaction networks focus solely on coarse-grained evolution types (e.g., merge, split), neglect fine-grained evolution magnitudes (e.g., expansion size), and fail to leverage stable friendship networks. To address these limitations, this paper proposes a unified framework that jointly models both evolution type and magnitude. Methodologically, we introduce the first end-to-end classification-regression joint learning model for this task; design a hybrid discriminative strategy to enhance separability among confusable evolution types; and integrate interaction and friendship networks via multi-source embedding and graph-structure-aware temporal community representation learning. Evaluated on three real-world datasets, our method achieves up to 12.6% improvement in evolution-type prediction accuracy and up to 18.3% reduction in mean absolute error (MAE) for magnitude prediction, significantly outperforming state-of-the-art baselines.

Technology Category

• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Machine Learning: Evolutionary Learning

Application Category

• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks
• Web Mining and Content Analysis: Models for Web evolution
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Interactive networks representing user participation and interactions in specific"events"are highly dynamic, with communities reflecting collective behaviors that evolve over time. Predicting these community evolutions is crucial for forecasting the trajectory of the related"event". Some models for community evolution prediction have been witnessed, but they primarily focused on coarse-grained evolution types (e.g., expand, dissolve, merge, split), often neglecting fine-grained evolution extents (e.g., the extent of community expansion). Furthermore, these models typically utilize only one network data (here is interactive network data) for dynamic community featurization, overlooking the more stable friendship network that represents the friendships between people to enrich community representations. To address these limitations, we propose a two-stage model that predicts both the type and extent of community evolution. Our model unifies multi-class classification for evolution type and regression for evolution extent within a single framework and fuses data from both interactive and friendship networks for a comprehensive community featurization. We also introduce a hybrid strategy to differentiate between evolution types that are difficult to distinguish. Experimental results on three datasets show the significant superiority of the proposed model over other models, confirming its efficacy in predicting community evolution in interactive networks.

Problem

• Predict community evolution in dynamic interactive networks.
• Incorporate friendship networks for enhanced community representation.
• Differentiate and predict both type and extent of community evolution.

Innovation

• Two-stage model for community evolution prediction
• Fuses interactive and friendship network data
• Combines multi-class classification and regression