A Diffusive Data Augmentation Framework for Reconstruction of Complex Network Evolutionary History

2025-01-11

AI Summary

Existing methods exhibit insufficient accuracy in inferring edge formation timestamps from static networks lacking temporal annotations, thereby hindering the understanding of dynamic systems such as protein–protein interactions and ecological evolution. To address this, we propose the first diffusion-based temporal network synthesis framework. Our approach introduces a cross-network contrastive learning architecture that jointly models structural and evolutionary temporal dependencies across multiple source networks. By integrating diffusion-augmented data generation, multi-network contrastive representation learning, and temporal graph neural networks, our method enables end-to-end reconstruction of evolutionary histories from static network inputs. Experiments demonstrate an average 16.98% improvement in cross-network edge timestamp prediction accuracy over prior methods; incorporating diffusion-augmented data further boosts performance by 5.46%. This advancement significantly alleviates the generalization bottleneck in temporal recovery from static network structures.

Technology Category

• Planning, Routing, and Scheduling: Temporal Planning
• Machine Learning: Evolutionary Learning
• Search and Optimization: Evolutionary Computation

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Web Mining and Content Analysis: Models for Web evolution
• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks

Abstract

The evolutionary processes of complex systems contain critical information regarding their functional characteristics. The generation time of edges provides insights into the historical evolution of various networked complex systems, such as protein-protein interaction networks, ecosystems, and social networks. Recovering these evolutionary processes holds significant scientific value, including aiding in the interpretation of the evolution of protein-protein interaction networks. However, existing methods are capable of predicting the generation times of remaining edges given a partial temporal network but often perform poorly in cross-network prediction tasks. These methods frequently fail in edge generation time recovery tasks for static networks that lack timestamps. In this work, we adopt a comparative paradigm-based framework that fuses multiple networks for training, enabling cross-network learning of the relationship between network structure and edge generation times. Compared to separate training, this approach yields an average accuracy improvement of 16.98%. Furthermore, given the difficulty in collecting temporal networks, we propose a novel diffusion-model-based generation method to produce a large number of temporal networks. By combining real temporal networks with generated ones for training, we achieve an additional average accuracy improvement of 5.46% through joint training.

Problem

• Temporal Network
• Complex Systems
• Evolution Prediction

Innovation

• Multi-temporal network analysis
• Simulated diffusion process
• Enhanced time prediction accuracy