@Article{cmc.2026.082651,
AUTHOR = {Suchang Yang, Hongtao Yu, Ruiyang Huang, Huansha Wang, Ran Li, Junzheng Li},
TITLE = {DyG-Hyena: Lightweight Temporal Modeling and Efficient Information Enhancement for Continuous-Time Dynamic Graph},
JOURNAL = {Computers, Materials \& Continua},
VOLUME = {},
YEAR = {},
NUMBER = {},
PAGES = {{pages}},
URL = {http://www.techscience.com/cmc/online/detail/27199},
ISSN = {1546-2226},
ABSTRACT = {Modeling dynamic graphs in continuous time is critical for applications such as user behavior prediction and recommendation systems. These models can effectively capture fine-grained and long-term temporal dependencies. However, existing approaches often suffer from high computational costs and optimization difficulties, especially when handling time-sorted neighborhood sequences over long horizons. In this work, we propose DyG-Hyena, a novel continuous-time dynamic graph learning framework that combines conditional variational autoencoder (CVAE)-assisted temporal modeling with efficient feature fusion. Our approach has two main innovations: (i) Efficient temporal fusion—we replace the Transformer with an improved, lightweight Hyena module to model and fuse time-sorted neighborhood feature sequences, reducing computation of this process while maintaining accuracy. A CVAE layer is added before Hyena to capture relative time constraints, enhancing generalization for link prediction. (ii) Task-specific multi-dimensional information enhancement—for link prediction, we incorporate cross-order neighborhood intersection encoding; for node classification, we introduce statistical encoding of node features. Extensive experiments on benchmark dynamic graph datasets demonstrate that DyG-Hyena achieves excellent performance while substantially reducing temporal modeling complexity. Our code is available at <a href="https://github.com/yangchang666/DyG-Hyena" target="_blank">https://github.com/yangchang666/DyG-Hyena</a>.},
DOI = {10.32604/cmc.2026.082651}
}