Signed Graph Autoencoder for Explainable and Polarization-Aware Network Embeddings
Nakis, Nikolaos Kosma, Chrysoula Nikolentzos, Giannis Chatzianastasis, Michail Evdaimon, Iakovos Vazirgiannis, Michalis
Nakis, Nikolaos
Kosma, Chrysoula
Nikolentzos, Giannis
Chatzianastasis, Michail
Evdaimon, Iakovos
Vazirgiannis, Michalis
Supervisor
Department
Machine Learning
Embargo End Date
Type
Conference proceeding
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Autoencoders based on Graph Neural Networks (GNNs) have garnered significant attention in recent years for their ability to learn informative latent representations of complex topologies, such as graphs. Despite the prevalence of Graph Autoencoders, there has been limited focus on developing and evaluating explainable neural-based graph generative models specifically designed for signed networks. To address this gap, we propose the Signed Graph Archetypal Autoencoder (SGAAE) framework. SGAAE extracts node-level representations that express node memberships over distinct extreme profiles, referred to as archetypes, within the network. This is achieved by projecting the graph onto a learned polytope, which governs its polarization. The framework employs the Skellam distribution for analyzing signed networks combined with relational archetypal analysis and GNNs. Our experimental evaluation demonstrates the SGAAE's capability to successfully infer node memberships over underlying latent structures while extracting competing communities. Additionally, we introduce the 2-level network polarization problem and show how SGAAE is able to characterize such a setting. The proposed model achieves high performance in different tasks of signed link prediction across four real-world datasets, outperforming several baseline models. Finally, SGAAE allows for interpretable visualizations in the polytope space, revealing the distinct aspects of the network, as well as, how nodes are expressing them. (Code available at: https://github.com/Nicknakis/SGAAE).
Citation
N. Nakis, C. Kosma, G. Nikolentzos, M. Chatzianastasis, I. Evdaimon, and M. Vazirgiannis, “Signed Graph Autoencoder for Explainable and Polarization-Aware Network Embeddings,” in Proc. 28th Int. Conf. Artif. Intell. Stat. (AISTATS 2025), vol. 258, Proc. Mach. Learn. Res., Mai Khao, Thailand, May 3–5, 2025, pp. 496–504.
Source
Proceedings of Machine Learning Research
Conference
28th International Conference on Artificial Intelligence and Statistics, AISTATS 2025
Keywords
Elman Neural Networks, Graph Embeddings, Graph Neural Networks, Graph Theory, As Graph, Auto Encoders, Complex Topology, Generative Model, Learn+, Network Embedding, Polytopes, Signed Graphs, Signed Networks, Polarization
Subjects
Source
28th International Conference on Artificial Intelligence and Statistics, AISTATS 2025
Publisher
ML Research Press