Semi-Supervised Learning via Cross-Prediction-Powered Inference for Wireless Systems
In many wireless application scenarios, acquiring labeled data can be prohibitively costly, requiring complex optimization processes or measurement campaigns. Semi-supervised learning leverages unlabeled samples to augment the available dataset by assigning synthetic labels obtained via machine lear...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Transactions on Machine Learning in Communications and Networking |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10758826/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850051516291874816 |
|---|---|
| author | Houssem Sifaou Osvaldo Simeone |
| author_facet | Houssem Sifaou Osvaldo Simeone |
| author_sort | Houssem Sifaou |
| collection | DOAJ |
| description | In many wireless application scenarios, acquiring labeled data can be prohibitively costly, requiring complex optimization processes or measurement campaigns. Semi-supervised learning leverages unlabeled samples to augment the available dataset by assigning synthetic labels obtained via machine learning (ML)-based predictions. However, treating the synthetic labels as true labels may yield worse-performing models as compared to models trained using only labeled data. Inspired by the recently developed prediction-powered inference (PPI) framework, this work investigates how to leverage the synthetic labels produced by an ML model, while accounting for the inherent bias concerning true labels. To this end, we first review PPI and its recent extensions, namely tuned PPI and cross-prediction-powered inference (CPPI). Then, we introduce two novel variants of PPI. The first, referred to as tuned CPPI, provides CPPI with an additional degree of freedom in adapting to the quality of the ML-based labels. The second, meta-CPPI (MCPPI), extends tuned CPPI via the joint optimization of the ML labeling models and of the parameters of interest. Finally, we showcase two applications of PPI-based techniques in wireless systems, namely beam alignment based on channel knowledge maps in millimeter-wave systems and received signal strength information-based indoor localization. Simulation results show the advantages of PPI-based techniques over conventional approaches that rely solely on labeled data or that apply standard pseudo-labeling strategies from semi-supervised learning. Furthermore, the proposed tuned CPPI method is observed to guarantee the best performance among all benchmark schemes, especially in the regime of limited labeled data. |
| format | Article |
| id | doaj-art-7d2c558215e74737ac2a65df9e7a2e38 |
| institution | DOAJ |
| issn | 2831-316X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Transactions on Machine Learning in Communications and Networking |
| spelling | doaj-art-7d2c558215e74737ac2a65df9e7a2e382025-08-20T02:53:07ZengIEEEIEEE Transactions on Machine Learning in Communications and Networking2831-316X2025-01-013304410.1109/TMLCN.2024.350354310758826Semi-Supervised Learning via Cross-Prediction-Powered Inference for Wireless SystemsHoussem Sifaou0https://orcid.org/0000-0003-0630-7073Osvaldo Simeone1https://orcid.org/0000-0001-9898-3209Department of Engineering, King’s Communications, Learning and Information Processing (KCLIP) Laboratory, Centre for Intelligent Information Processing Systems (CIIPS), King’s College London, London, U.K.Department of Engineering, King’s Communications, Learning and Information Processing (KCLIP) Laboratory, Centre for Intelligent Information Processing Systems (CIIPS), King’s College London, London, U.K.In many wireless application scenarios, acquiring labeled data can be prohibitively costly, requiring complex optimization processes or measurement campaigns. Semi-supervised learning leverages unlabeled samples to augment the available dataset by assigning synthetic labels obtained via machine learning (ML)-based predictions. However, treating the synthetic labels as true labels may yield worse-performing models as compared to models trained using only labeled data. Inspired by the recently developed prediction-powered inference (PPI) framework, this work investigates how to leverage the synthetic labels produced by an ML model, while accounting for the inherent bias concerning true labels. To this end, we first review PPI and its recent extensions, namely tuned PPI and cross-prediction-powered inference (CPPI). Then, we introduce two novel variants of PPI. The first, referred to as tuned CPPI, provides CPPI with an additional degree of freedom in adapting to the quality of the ML-based labels. The second, meta-CPPI (MCPPI), extends tuned CPPI via the joint optimization of the ML labeling models and of the parameters of interest. Finally, we showcase two applications of PPI-based techniques in wireless systems, namely beam alignment based on channel knowledge maps in millimeter-wave systems and received signal strength information-based indoor localization. Simulation results show the advantages of PPI-based techniques over conventional approaches that rely solely on labeled data or that apply standard pseudo-labeling strategies from semi-supervised learning. Furthermore, the proposed tuned CPPI method is observed to guarantee the best performance among all benchmark schemes, especially in the regime of limited labeled data.https://ieeexplore.ieee.org/document/10758826/Prediction-powered inferencesemi-supervised learningchannel knowledge mapindoor localization |
| spellingShingle | Houssem Sifaou Osvaldo Simeone Semi-Supervised Learning via Cross-Prediction-Powered Inference for Wireless Systems IEEE Transactions on Machine Learning in Communications and Networking Prediction-powered inference semi-supervised learning channel knowledge map indoor localization |
| title | Semi-Supervised Learning via Cross-Prediction-Powered Inference for Wireless Systems |
| title_full | Semi-Supervised Learning via Cross-Prediction-Powered Inference for Wireless Systems |
| title_fullStr | Semi-Supervised Learning via Cross-Prediction-Powered Inference for Wireless Systems |
| title_full_unstemmed | Semi-Supervised Learning via Cross-Prediction-Powered Inference for Wireless Systems |
| title_short | Semi-Supervised Learning via Cross-Prediction-Powered Inference for Wireless Systems |
| title_sort | semi supervised learning via cross prediction powered inference for wireless systems |
| topic | Prediction-powered inference semi-supervised learning channel knowledge map indoor localization |
| url | https://ieeexplore.ieee.org/document/10758826/ |
| work_keys_str_mv | AT houssemsifaou semisupervisedlearningviacrosspredictionpoweredinferenceforwirelesssystems AT osvaldosimeone semisupervisedlearningviacrosspredictionpoweredinferenceforwirelesssystems |