Model Refinement Learning and an Example on Channel Estimation With Universal Noise Model
The DOI matches its Crossref record; 51 of the 51 references it cites were found in a registry or an index.
Abstract
Model-based method and data-based method are two basic approaches for the design of wireless communication systems. Model-based methods suffer from inaccurate modeling assumptions due to excessively complex environment. Recently, data-based methods have achieved remarkable performances in the communication system design without the knowledge of accurate model but encounter some challenges such as, lack of available labelled training data and explainability. In this paper, we propose a novel hybrid idea to integrate the strengths of both data and model-based methods, named model refinement learning, which is training affordable, theoretically interpretable and self-adapting. To show the idea more concretely, a novel channel estimation algorithm is proposed in the multiple-input single-output (MISO) system in the case where the noise model is unknown. In particular, we utilize a universal mixture of Gaussian (MoG) model, which can adaptively adjust the involved parameters to fit the true noise distribution by using observed data. We propose a novel variational inference framework to achieve automatical noise model refinement and design the corresponding online channel estimator. To reduce the online algorithm overhead, we propose a decoupled variational Bayesian method to achieve linear computational complexity. Simulations show that our proposed method outperforms both the model-based and data-based counterparts.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“For anomaly detection in microservices, TDAI is particularly relevant in edge and IoT scenarios, where embedded AI models are deployed close to the data source [237,238].”
From Anomaly detection and root-cause identification in microservices: a survey (2026) · cites this paper as [238]
Citations
Cites
Book Review: Pattern Recognition and Machine Learning
Nasrabadi, N. M. (2007) · Journal of Electronic Imaging · doi:10.1117/1.2819119 · Cited by 22,066 · cited 2×
“MoG distribution has been widely used in signal processing [30] and pattern recognition [31], which is a simple linear superposition of Gaussian components and can provide a richer class of density distributions [32].”
MethodAuto-Encoding Variational Bayes
Kingma, D. P., & Welling, M. (2013) · arXiv · doi:10.48550/arxiv.1312.6114 · Cited by 20,067
Fundamentals of Statistical Signal Processing: Estimation Theory
Sengijpta, S. K. (1995) · Technometrics · doi:10.1080/00401706.1995.10484391 · Cited by 11,076
Fundamentals of statistical signal processing: Estimation theory
Prasad, K. V. (1994) · Control Engineering Practice · doi:10.1016/0967-0661(94)90195-3 · Cited by 7,902
Pattern Recognition and Machine Learning
Neal, R. M. (2007) · Technometrics · doi:10.1198/tech.2007.s518 · Cited by 4,571
Graphical Models, Exponential Families, and Variational Inference
Wainwright, M. J., & Jordan, M. I. (2007) · now publishers, Inc. eBooks · doi:10.1561/9781601981851 · Cited by 2,959
Power of Deep Learning for Channel Estimation and Signal Detection in OFDM Systems
Ye, H., Li, G. Y., & Juang, B.-H. (2018) · IEEE Wireless Communications Letters · doi:10.1109/lwc.2017.2757490 · Cited by 2,000 · cited 4×
“Such a phenomenon is significantly different from the LMMSE estimator or other data-based and model-based DL methods [13], [22], in which the estimators are fixed after the training steps.”
BackgroundMethodInfluentialGraphical Models, Exponential Families, and Variational Inference
Wainwright, M. J., & Jordan, M. I. (2008) · Foundations and Trends® in Machine Learning · doi:10.1561/2200000001 · Cited by 1,820 · cited 1×
“And the distribution q ( θ ) can be factorized as This factorized form of q ( θ ) in the variational inference corresponds to an approximation framework developed in the statistical physics literature called mean field theory [42].”
MethodA Constructive Definition of Dirichlet Priors
Sethuraman, J. (1991) · doi:10.21236/ada238689 · Cited by 1,572
Malware traffic classification using convolutional neural network for representation learning
Wang, W., Zhu, M., Zeng, X., Ye, X., & Sheng, Y. (2017) · 2017 International Conference on Information Networking (ICOIN) · doi:10.1109/icoin.2017.7899588 · Cited by 1,177 · cited 1×
“Due to the powerful mechanism, DL has made great progress in network traffic prediction [1], [2], data traffic classification [3], [4], network routing [5], network scheduling [6] and resource allocation [7], [8], etc.”
Background
Cited by
Sadeghi, A., Bellavista, P., Song, W., & Yazdani-Asrami, M. (2024) · IEEE Access · doi:10.1109/access.2024.3371902 · Cited by 100
“…control and reconfiguration commands in the proximity of their actuators; in addition, distributed DT on industrial gateways or MEC nodes can continue the training/learning process also locally, via emerging machine learning techniques such as refinement learning [211] and federated learning [212].”
Design and Implementation of 5G e-Health Systems: Technologies, Use Cases, and Future Challenges
Zhang, D., Rodrigues, J. J. P. C., Zhai, Y., & Sato, T. (2021) · IEEE Communications Magazine · doi:10.1109/mcom.001.2100035 · Cited by 38
Deep Learning Based Efficient Symbol-Level Precoding Design for MU-MISO Systems
Bo, Z., Liu, R., Li, M., & Liu, Q. (2021) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2021.3093079 · Cited by 21
“The authors in [8], [9] exploited learning-based schemes for more accurate channel estimation.”
BackgroundGrouping-Based Joint Active User Detection and Channel Estimation With Massive MIMO
Jiang, J., & Wang, H. (2021) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2021.3111104 · Cited by 15
“On the other hand, to deal with the liner mixing of sparse vector, some approximations are considered, such as AMP approximation [17], mean field (MF) approximation [33], [42].”
BackgroundSelf-citationRobust 3-D AOA Localization Against Malicious Attacks in Non-Gaussian Noise
Yan, Q., Wang, H., Chen, Y., & Gao, C. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3373649 · Cited by 12
“With the demand of autonomous robots and vehicle of the Internet of Thing (IoT) in the forthcoming sixth-generation (6G) wireless networks, the localization accuracy faces new challenges under malicious attacks in complex signal propagation environment with channel variations [1], [2], [3], [4].”
BackgroundSelf-citation
Metadata
- Authors
- Wang, H.-M., Jiang, J.-C., & Wang, Y.-N.
- Affiliations
- Xi'an Jiaotong University (CN)
- ORCID
- Wang, Hui-Ming
- Venue
- IEEE Journal on Selected Areas in Communications
- Published
- 2021-01
- Volume
- 39
- Issue
- 1
- Pages
- 31-46
- ISSN
- 0733-8716 (ISSN-L)
- 1558-0008
- OpenAlex
- W3100624467
- Cited by
- 14
- References
- 51
- Citations by year
- 2026: 1 · 2024: 3 · 2023: 2 · 2022: 2 · 2021: 6
- FWCI
- 0.86
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Journal on Selected Areas in Communications (publishedVersion)
- Funders
- National Natural Science Foundation of China (61941118, 61941105)
- National Key Research and Development Program of China (2019YFE0113200)
- Innovation Team Research Fund of Shaanxi Province (2019TD-013)
- Topics
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Wireless Communication Techniques
- Physical Sciences › Computer Science › Computer Networks and Communications › Wireless Communication Networks Research
- Physical Sciences › Engineering › Control and Systems Engineering › Control Systems and Identification
- Keywords
- channel estimation, variational inference, MISO systems, wireless communication system design
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Model Refinement Learning and an Example on Channel Estimation With Universal Noise Model. https://app.cochat.ai/papers/10.1109/jsac.2020.3036964
- The paper
- Wang, H.-M., Jiang, J.-C., & Wang, Y.-N. (2021). Model Refinement Learning and an Example on Channel Estimation With Universal Noise Model. IEEE Journal on Selected Areas in Communications. https://doi.org/10.1109/jsac.2020.3036964
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.