Behavioral-Similarity and Clustering-Based Methods for Static Graph Estimation in Hybrid GNNs (Student Abstract)
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (48) · 41340-41342
DOI: 10.1609/aaai.v40i48.42262 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Ryusei Otani und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).
Abstract (Originalsprache)
In this study, we propose two methods to estimate static graphs from a single dynamic graph and integrate them into hybrid Graph Neural Networks (GNNs), which combine long-term static structure with transient dynamic interactions. Since static graphs are often unavailable and attributes may be difficult to use at scale or under privacy constraints, we introduce: (i) a “behavioral similarity” estimator based on normalized co-occurrence, which requires no attributes, and (ii) an attribute-aware K-means + k-NN estimator that is more efficient than cosine similarity. Experiments on multiple real-world datasets show that both methods consistently improve predictive accuracy and training efficiency, underscoring the importance of static graph choice in hybrid GNNs.
Zitieren
APA
Otani, R., Namikoshi, K., Sakurai, Y., Guo, M., & Oyama, S. (2026). Behavioral-Similarity and Clustering-Based Methods for Static Graph Estimation in Hybrid GNNs (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 40(48), 41340-41342. https://doi.org/10.1609/aaai.v40i48.42262
Vancouver
Otani R, Namikoshi K, Sakurai Y, Guo M, Oyama S. Behavioral-Similarity and Clustering-Based Methods for Static Graph Estimation in Hybrid GNNs (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(48):41340-41342. doi:10.1609/aaai.v40i48.42262
BibTeX
@article{Otani2026,
author = {Otani, Ryusei and Namikoshi, Keichi and Sakurai, Yuko and Guo, Mingyu and Oyama, Satoshi},
title = {Behavioral-Similarity and Clustering-Based Methods for Static Graph Estimation in Hybrid GNNs (Student Abstract)},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {48},
pages = {41340--41342},
doi = {10.1609/aaai.v40i48.42262}
}
EUVIMED