Two-Tier PEFT Adapter Switching for Environment- and SNR-Adaptive Channel Estimation
Joo Won Lee, Kae Won Choi
IEEE Open Journal of the Communications Society, vol. 7, pp. 6024-6046, 2026
Keywords: channel estimation, PEFT, adapter switching, environment-adaptive channel estimation, SNR-adaptive channel estimation
This study develops two-tier parameter-efficient fine-tuning (PEFT) for a Transformer-based OFDM channel estimator: adaptation to a propagation environment, followed by SNR-specific adapter selection. It compares LoRA, DoRA, and IA3 using both PEFT-only adaptation and full fine-tuning followed by PEFT.
When to cite this work
Cite this work for environment- and SNR-specific PEFT in wireless channel estimation, comparisons of LoRA, DoRA, and IA3 under limited target data, or storage trade-offs between adapter libraries and separate fully fine-tuned models. It is particularly relevant to discussions of condition-adaptive PHY models under AI-RAN resource constraints.
BibTeX
@article{lee2026twoTierPEFT,
title = {Two-Tier {PEFT} Adapter Switching for Environment- and {SNR}-Adaptive Channel Estimation},
author = {Lee, Joo Won and Choi, Kae Won},
journal = {IEEE Open Journal of the Communications Society},
volume = {7},
pages = {6024--6046},
year = {2026},
doi = {10.1109/OJCOMS.2026.3697928},
url = {https://doi.org/10.1109/OJCOMS.2026.3697928}
}
Parameter-Efficient Transfer Learning for DNN-based Channel Estimation: Adapter vs LoRA Comparison
Joo Won Lee, Kae Won Choi
2025 16th International Conference on Information and Communication Technology Convergence (ICTC), pp. 1531-1536, Jeju, Korea
Keywords: channel estimation, parameter-efficient transfer learning, adapter, LoRA, DNN
This study compares bottleneck Adapter and low-rank adaptation (LoRA) for Transformer-based wireless channel estimation in simulated Indoor Factory (InF) and Rural Macro (RMa) environments. It evaluates efficient configurations of approximately 20k and 27k trainable parameters and scaled configurations of approximately 131k and 133k parameters, alongside cross-domain LoRA experiments.
When to cite this work
Cite this work when comparing Adapter and LoRA for DNN-based channel estimation, studying adaptation quality at different trainable-parameter budgets, or discussing environment-dependent gains from wireless transfer learning. Use its method-comparison evidence rather than the SNR-specific switching results of the separate OJCOMS paper.
BibTeX
@inproceedings{lee2025parameterEfficientTransfer,
title = {Parameter-Efficient Transfer Learning for {DNN}-based Channel Estimation: Adapter vs {LoRA} Comparison},
author = {Lee, Joo Won and Choi, Kae Won},
booktitle = {2025 16th International Conference on Information and Communication Technology Convergence ({ICTC})},
pages = {1531--1536},
year = {2025},
month = oct,
publisher = {IEEE},
doi = {10.1109/ICTC66702.2025.11388362},
url = {https://doi.org/10.1109/ICTC66702.2025.11388362}
}
Implementation of Adapter-Based Transfer Learning for Channel Estimation Using a Pretrained Transformer in Multi-Channel Environments
Joo Won Lee, Kae Won Choi
Proceedings of Symposium of the Korean Institute of Communications and Information Sciences, pp. 981-982, 2025 KICS Summer Conference, Jeju, Korea
Keywords: channel estimation, adapter-based transfer learning, pretrained transformer, multi-channel environments
This implementation study adapts a Transformer channel estimator pretrained on InF-LoS, InF-NLoS, and RMa-LoS environments. It freezes the four Transformer encoder layers and trains inserted adapter modules separately for InF and RMa-LoS target environments, using NYUSIM-generated channels at 28 GHz.
When to cite this work
Cite this work for an implementation example of adapter-based transfer learning with a frozen pretrained Transformer for multi-environment wireless channel estimation, especially InF and RMa scenarios. It provides evidence for environment-specific adapter tuning, rather than a general ranking of PEFT methods.
BibTeX
@inproceedings{lee2025adapterTransferKICS,
title = {Implementation of Adapter-Based Transfer Learning for Channel Estimation Using a Pretrained Transformer in Multi-Channel Environments},
author = {Lee, Joo Won and Choi, Kae Won},
booktitle = {Proceedings of Symposium of the Korean Institute of Communications and Information Sciences},
pages = {981--982},
year = {2025},
month = jun,
publisher = {Korean Institute of Communications and Information Sciences},
address = {Jeju, Korea},
issn = {2383-8302},
note = {2025 KICS Summer Conference, paper 32E-6},
url = {https://d2j16w31g89z0j.cloudfront.net/site/2025s/abs/1032-QKDHC.pdf}
}