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

TL;DR

This paper introduces a diffusive data augmentation framework that enhances the reconstruction of complex network evolutionary histories by combining cross-network learning and diffusion-model-based generation, significantly improving prediction accuracy.

Contribution

It proposes a novel framework that fuses multiple networks for training and introduces a diffusion-model-based method to generate temporal networks, improving cross-network edge generation time prediction.

Findings

Average accuracy improved by 16.98% with multi-network training.

Additional 5.46% accuracy gain through joint training with generated networks.

Framework effectively reconstructs evolutionary processes of complex 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.