DYANE: DYnamic Attributed Node rolEs Generative Model (CIKM 2023)
Full documentation will be added soon.
PDF: DYANE: DYnamic Attributed Node RolEs Generative Model
Video: CIKM 2023 (ACM DL)
Authors: Giselle Zeno and Jennifer Neville
If you use this code, please cite:
@inproceedings{Zeno2023,
author = {Zeno, Giselle and Neville, Jennifer},
title = {DYANE: DYnamic Attributed Node RolEs Generative Model},
year = {2023},
isbn = {9798400701245},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3583780.3614858},
doi = {10.1145/3583780.3614858},
abstract = {Recent work has shown that modeling higher-order structures, such as motifs or graphlets, can capture the complex network structure and dynamics in a variety of graph domains (e.g., social sciences, biology, chemistry). However, many dynamic networks are not only rich in structure, but also in content information. For example, an academic citation network has content such as the title and abstracts of the papers. Currently, there is a lack of generative models for dynamic networks that also generate content. To address this gap, in this work we propose DYnamic Attributed Node rolEs (DYANE)-a generative model that (i) captures network structure dynamics through temporal motifs, and (ii) extends the structural roles of nodes in motifs (e.g., a node acting as a hub in a wedge) to roles that generate content embeddings. We evaluate DYANE on real-world networks against other dynamic graph generative model baselines. DYANE outperforms the baselines in graph structure and node behavior, improving the KS score for graph metrics by 21-31\% and node metrics by 17-27\% on average, and produces content embeddings similar to the observed network. We also derive a methodology to evaluate the content embeddings generated by nodes, taking into account keywords extracted from the content (as topic representations), and using distance metrics.},
booktitle = {Proceedings of the 32nd ACM International Conference on Information and Knowledge Management},
pages = {3144–3153},
numpages = {10},
keywords = {network evolution, dynamic attributed networks, graph neural networks, motifs, temporal attributed graphs},
location = {Birmingham, United Kingdom},
series = {CIKM '23}
}