Network-first Separate Training with Raw Dataset Sharing: A Training Approach for AI/ML-Driven CSI Feedback
Saini A, Kim JH, Tehrani AA, Xing Y, Gerstacker W (2024)
Publication Type: Conference contribution
Publication year: 2024
Publisher: Institute of Electrical and Electronics Engineers Inc.
Pages Range: 1950-1955
Conference Proceedings Title: 2024 IEEE International Conference on Communications Workshops, ICC Workshops 2024
Event location: Denver, CO, USA
ISBN: 9798350304053
DOI: 10.1109/ICCWorkshops59551.2024.10615736
Abstract
This study explores the enhancement of channel state information (CSI) feedback in wireless communication systems by applying artificial intelligence/machine learning (AI/ML). The traditional joint training of an AI encoder at the user equipment (UE) and an AI decoder at the network (NW) side presents several challenges. Jointly trained models require sharing proprietary information, increase vulnerability to adversarial attacks, and are less suited for multi-user or multi-base station scenarios. In response to these challenges, the approach of training model entities independently has garnered interest, centring on two primary methods: UE-first separate training and NW-first sepa-rate training. Empirical findings from Release 18 AI/ML for Air Interface studies indicate that the UE-first approach yields better performance. However, this method limits the network's flexibility to accommodate distinct NW -side decoder model configurations tailored to various cells and sites. In response, this paper intro-duces a novel enhancement to the conventional NW-first separate training strategy to achieve performance gains, particularly at low quantizer resolution. Our results confirm that both the improved NW-first and UE-first strategies deliver comparable performance, both nearing joint training benchmarks.
Authors with CRIS profile
Involved external institutions
Germany (DE)How to cite
APA:
Saini, A., Kim, J.H., Tehrani, A.A., Xing, Y., & Gerstacker, W. (2024). Network-first Separate Training with Raw Dataset Sharing: A Training Approach for AI/ML-Driven CSI Feedback. In Matthew Valenti, David Reed, Melissa Torres (Eds.), 2024 IEEE International Conference on Communications Workshops, ICC Workshops 2024 (pp. 1950-1955). Denver, CO, USA: Institute of Electrical and Electronics Engineers Inc..
MLA:
Saini, Aakash, et al. "Network-first Separate Training with Raw Dataset Sharing: A Training Approach for AI/ML-Driven CSI Feedback." Proceedings of the 59th Annual IEEE International Conference on Communications Workshops, ICC Workshops 2024, Denver, CO, USA Ed. Matthew Valenti, David Reed, Melissa Torres, Institute of Electrical and Electronics Engineers Inc., 2024. 1950-1955.
BibTeX: Download