Empowering Interdisciplinary Insights with Dynamic Graph Embedding Trajectories

Yiqiao Jin, Andrew Zhao, Yeon-Chang Lee, Meng Ye, Ajay Divakaran, Srijan Kumar

Keywords: Visualization, Temporal Graph Neural Networks, Interpretability, Dynamic Graphs

TL;DR: We present DyGETViz, an open-source framework that visualizes dynamic graphs using temporal graph neural networks to reveal complex structural patterns across diverse domains like linguistics, finance, biology, and social network.

Abstract: We present DyGETViz, a novel framework for visualizing discrete-time dynamic graph (DTDGs) that are ubiquitous across diverse real-world systems, such as social networks, linguistics, international relations, and computational finance. By leveraging the inherent temporal dynamics in dynamic graphs, DyGETViz effectively captures both micro- and macro-level structural shifts within these graphs, offering a robust method for representing complex and massive dynamic graphs. Through its implementation, DyGETViz has revealed or confirmed various critical insights. These include the diversity of content sharing patterns and the degree of specialization within online communities, the chronological evolution of lexicons across decades, and the distinct trajectories exhibited by aging-related and non-related genes. Importantly, DyGETViz enhances the accessibility of scientific findings to non-domain experts by simplifying the complexities of dynamic graphs. Our framework is anonymously available at https://anonymous.4open.science/r/dygetviz/README.md. It will be released as an open-source Python package for use across diverse disciplines.

Format: Long paper, up to 8 pages.

Submission Number: 12