Resource-Efficient CSI Prediction: A Gated Fusion and Factorized Projection Approach
IEEE Communications Letters · 2026 · 30 · 1979-1983
DOI: 10.1109/lcomm.2026.3691476 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Communications Letters, 2026. Verfasst von Mohammad Hussain und 5 weiteren Autor:innen. Die Arbeit nennt 19 Literaturangaben. Gefördert von: Scientific and Technological Research Council of Turkey (TUBITAK) 1711 Project.
Abstract (Originalsprache)
Accurate Channel State Information (CSI) prediction is essential for dynamic multiple-input multiple-output (MIMO) systems but remains computationally demanding. This letter proposes a resource-efficient predictor that combines a gated recurrent unit (GRU) encoder with Luong attention, a bottleneck gated fusion module, and a Dimension-wise Separable Linear Head (DSLH). The gated fusion module integrates local recurrent features with global attention context, while the DSLH reduces the cost of the output mapping. Evaluated on 3GPP TR 38.901-compliant channels, the proposed model achieves an average NMSE of −13.84 dB with 26% fewer parameters and approximately $2.3\times $ higher inference throughput than a dimension-matched LinFormer baseline. The proposed model is best suited to LOS and mixed-condition scenarios, offering a practical accuracy–efficiency trade-off for short-horizon CSI prediction at moderate sequence lengths.
Förderung
- Scientific and Technological Research Council of Turkey (TUBITAK) 1711 Project
Zitieren
APA
Hussain, M., Adibag, M., Gurer, D., Kalem, G., Serin, K., & Coleri, S. (2026). Resource-Efficient CSI Prediction: A Gated Fusion and Factorized Projection Approach. IEEE Communications Letters, 30, 1979-1983. https://doi.org/10.1109/lcomm.2026.3691476
Vancouver
Hussain M, Adibag M, Gurer D, Kalem G, Serin K, Coleri S. Resource-Efficient CSI Prediction: A Gated Fusion and Factorized Projection Approach. IEEE Communications Letters. 2026;30:1979-1983. doi:10.1109/lcomm.2026.3691476
BibTeX
@article{Hussain2026,
author = {Hussain, Mohammad and Adibag, Maedeh and Gurer, Dilara and Kalem, Gokhan and Serin, Kerim and Coleri, Sinem},
title = {Resource-Efficient CSI Prediction: A Gated Fusion and Factorized Projection Approach},
journal = {IEEE Communications Letters},
year = {2026},
volume = {30},
pages = {1979--1983},
doi = {10.1109/lcomm.2026.3691476}
}
EUVIMED