Content popularity prediction based on quantized federated Bayesian learning in fog radio access networks
In this paper, we investigate the content popularity prediction problem in cache-enabled fog radio access networks (F-RANs). In order to predict the content popularity with high accuracy and low complexity, we propose a Gaussian process based regressor to model the content request pattern. Firstly,...
| Main Authors: | , , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/172071 |
| _version_ | 1811690716725772288 |
|---|---|
| author | Tao, Yunwei Jiang, Yanxiang Zheng, Fu-Chun Wang, Zhiheng Zhu, Pengcheng Tao, Meixia Niyato, Dusit You, Xiaohu |
| author2 | School of Computer Science and Engineering |
| author_facet | School of Computer Science and Engineering Tao, Yunwei Jiang, Yanxiang Zheng, Fu-Chun Wang, Zhiheng Zhu, Pengcheng Tao, Meixia Niyato, Dusit You, Xiaohu |
| author_sort | Tao, Yunwei |
| collection | NTU |
| description | In this paper, we investigate the content popularity prediction problem in cache-enabled fog radio access networks (F-RANs). In order to predict the content popularity with high accuracy and low complexity, we propose a Gaussian process based regressor to model the content request pattern. Firstly, the relationship between content features and popularity is captured by our proposed model. Then, we utilize Bayesian learning to train the model parameters, which is robust to overfitting. However, Bayesian methods are usually unable to find a closed-form expression of the posterior distribution. To tackle this issue, we apply a stochastic variance reduced gradient Hamiltonian Monte Carlo (SVRG-HMC) method to approximate the posterior distribution. To utilize the computing resource of fog access points (F-APs) and also reduce the communication overhead, we propose a quantized federated learning (FL) framework combining with Bayesian learning. The proposed quantized federated Bayesian learning framework allows each F-AP to send gradients to the cloud server after quantizing and encoding. It can achieve a tradeoff between prediction accuracy and communication overhead effectively. Simulation results show that the performance of our proposed policy outperforms the considered baseline policies. |
| first_indexed | 2024-10-01T06:08:25Z |
| format | Journal Article |
| id | ntu-10356/172071 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T06:08:25Z |
| publishDate | 2023 |
| record_format | dspace |
| spelling | ntu-10356/1720712023-11-21T05:00:48Z Content popularity prediction based on quantized federated Bayesian learning in fog radio access networks Tao, Yunwei Jiang, Yanxiang Zheng, Fu-Chun Wang, Zhiheng Zhu, Pengcheng Tao, Meixia Niyato, Dusit You, Xiaohu School of Computer Science and Engineering Engineering::Computer science and engineering Bayesian Learning Federated Learning In this paper, we investigate the content popularity prediction problem in cache-enabled fog radio access networks (F-RANs). In order to predict the content popularity with high accuracy and low complexity, we propose a Gaussian process based regressor to model the content request pattern. Firstly, the relationship between content features and popularity is captured by our proposed model. Then, we utilize Bayesian learning to train the model parameters, which is robust to overfitting. However, Bayesian methods are usually unable to find a closed-form expression of the posterior distribution. To tackle this issue, we apply a stochastic variance reduced gradient Hamiltonian Monte Carlo (SVRG-HMC) method to approximate the posterior distribution. To utilize the computing resource of fog access points (F-APs) and also reduce the communication overhead, we propose a quantized federated learning (FL) framework combining with Bayesian learning. The proposed quantized federated Bayesian learning framework allows each F-AP to send gradients to the cloud server after quantizing and encoding. It can achieve a tradeoff between prediction accuracy and communication overhead effectively. Simulation results show that the performance of our proposed policy outperforms the considered baseline policies. This work was supported in part by the National Natural Science Foundation of China under Grant 61971129, in part by the National Key Research and Development Program under Grant 2021YFB2900300, and in part by the Shenzhen Science and Technology Program under Grant KQTD20190929172545139. 2023-11-21T05:00:48Z 2023-11-21T05:00:48Z 2023 Journal Article Tao, Y., Jiang, Y., Zheng, F., Wang, Z., Zhu, P., Tao, M., Niyato, D. & You, X. (2023). Content popularity prediction based on quantized federated Bayesian learning in fog radio access networks. IEEE Transactions On Communications, 71(2), 893-907. https://dx.doi.org/10.1109/TCOMM.2022.3229679 0090-6778 https://hdl.handle.net/10356/172071 10.1109/TCOMM.2022.3229679 2-s2.0-85147201631 2 71 893 907 en IEEE Transactions on Communications © 2023 IEEE. All rights reserved. |
| spellingShingle | Engineering::Computer science and engineering Bayesian Learning Federated Learning Tao, Yunwei Jiang, Yanxiang Zheng, Fu-Chun Wang, Zhiheng Zhu, Pengcheng Tao, Meixia Niyato, Dusit You, Xiaohu Content popularity prediction based on quantized federated Bayesian learning in fog radio access networks |
| title | Content popularity prediction based on quantized federated Bayesian learning in fog radio access networks |
| title_full | Content popularity prediction based on quantized federated Bayesian learning in fog radio access networks |
| title_fullStr | Content popularity prediction based on quantized federated Bayesian learning in fog radio access networks |
| title_full_unstemmed | Content popularity prediction based on quantized federated Bayesian learning in fog radio access networks |
| title_short | Content popularity prediction based on quantized federated Bayesian learning in fog radio access networks |
| title_sort | content popularity prediction based on quantized federated bayesian learning in fog radio access networks |
| topic | Engineering::Computer science and engineering Bayesian Learning Federated Learning |
| url | https://hdl.handle.net/10356/172071 |
| work_keys_str_mv | AT taoyunwei contentpopularitypredictionbasedonquantizedfederatedbayesianlearninginfogradioaccessnetworks AT jiangyanxiang contentpopularitypredictionbasedonquantizedfederatedbayesianlearninginfogradioaccessnetworks AT zhengfuchun contentpopularitypredictionbasedonquantizedfederatedbayesianlearninginfogradioaccessnetworks AT wangzhiheng contentpopularitypredictionbasedonquantizedfederatedbayesianlearninginfogradioaccessnetworks AT zhupengcheng contentpopularitypredictionbasedonquantizedfederatedbayesianlearninginfogradioaccessnetworks AT taomeixia contentpopularitypredictionbasedonquantizedfederatedbayesianlearninginfogradioaccessnetworks AT niyatodusit contentpopularitypredictionbasedonquantizedfederatedbayesianlearninginfogradioaccessnetworks AT youxiaohu contentpopularitypredictionbasedonquantizedfederatedbayesianlearninginfogradioaccessnetworks |