Behavioral-Similarity and Clustering-Based Methods for Static Graph Estimation in Hybrid GNNs (Student Abstract)
Ryusei Otani, Keichi Namikoshi, Yuko Sakurai, Mingyu Guo, Satoshi Oyama
Abstract
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.
BibTeX
@inproceedings{aaai2026_behavioralsimila,
title = {Behavioral-Similarity and Clustering-Based Methods for Static Graph Estimation in Hybrid GNNs (Student Abstract)},
author = {Ryusei Otani and Keichi Namikoshi and Yuko Sakurai and Mingyu Guo and Satoshi Oyama},
booktitle = {AAAI 2026},
year = {2026}
}