Transfer Learning and Meta Learning-Based Fast Downlink Beamforming Adaptation

@article{Yuan2021TransferLA,
  title={Transfer Learning and Meta Learning-Based Fast Downlink Beamforming Adaptation},
  author={Yi Yuan and Gan Zheng and Kai-Kit Wong and Bj{\"o}rn E. Ottersten and Zhi-Quan Luo},
  journal={IEEE Transactions on Wireless Communications},
  year={2021},
  volume={20},
  pages={1742-1755}
}
  • Yi Yuan, G. Zheng, +2 authors Zhi-Quan Luo
  • Published 2 November 2020
  • Computer Science, Mathematics
  • IEEE Transactions on Wireless Communications
This article studies fast adaptive beamforming optimization for the signal-to-interference-plus-noise ratio balancing problem in a multiuser multiple-input single-output downlink system. Existing deep learning based approaches to predict beamforming rely on the assumption that the training and testing channels follow the same distribution which may not hold in practice. As a result, a trained model may lead to performance deterioration when the testing network environment changes. To deal with… Expand

Figures and Tables from this paper

Embedding Model Based Fast Meta Learning for Downlink Beamforming Adaptation
  • Juping Zhang, Yi Yuan, Gan Zheng, I. Krikidis, Kai-Kit Wong
  • Computer Science, Engineering
  • IEEE Transactions on Wireless Communications
  • 2021
TLDR
A simple yet effective adaptive framework to solve the mismatch issue, which trains an embedding model as a transferable feature extractor, followed by fitting the support vector regression, which can be applied to general radio resource management problems. Expand
Learning to Continuously Optimize Wireless Resource in a Dynamic Environment: A Bilevel Optimization Perspective
TLDR
This work proposes to build the notion of continual learning (CL) into wireless system design, so that the learning model can incrementally adapt to the new episodes, without forgetting knowledge learned from the previous episodes. Expand
Predicting Flat-Fading Channels via Meta-Learned Closed-Form Linear Filters and Equilibrium Propagation
  • Sangwoo Park, O. Simeone
  • Computer Science, Engineering
  • ArXiv
  • 2021
TLDR
This paper develops an offline low-complexity solution based on linear filtering via a meta-trained quadratic regularization and an online method based on gradient descent and equilibrium propagation (EP) that has the capacity to approach the genie-aided LMMSE solution with a small number of training data points. Expand
Learning to Continuously Optimize Wireless Resource in Episodically Dynamic Environment
TLDR
This work develops a methodology that enables data-driven methods to continuously learn and optimize in a dynamic environment by proposing a continual learning (CL) framework for wireless systems, which can incrementally adapt the learning models to the new episodes, without forgetting models learned from the previous episodes. Expand
Meta-Reinforcement Learning Based Resource Allocation for Dynamic V2X Communications
  • Yi Yuan, Gan Zheng, Kai-Kit Wong, K. Letaief
  • Computer Science, Mathematics
  • IEEE Transactions on Vehicular Technology
  • 2021
TLDR
A deep reinforcement learning (DRL)-based resource allocation algorithm to improve the performance of both V2I and V2V links and a meta-based DRL algorithm to enhance the fast adaptability of the resource allocation policy in the dynamic environment. Expand
Algorithm Unrolling for Massive Access via Deep Neural Network with Theoretical Guarantee
TLDR
This paper proposes a novel algorithm unrolling framework based on the deep neural network to simultaneously achieve low computational complexity and high robustness for solving the JADCE problem, and maps the original iterative shrinkage thresholding algorithm into an unrolled recurrent neural network (RNN). Expand
A Joint Energy and Latency Framework for Transfer Learning Over 5G Industrial Edge Networks
TLDR
A transfer learning (TL)-enabled edge-CNN framework for 5G industrial edge networks with privacy-preserving characteristic that can achieve almost 85% prediction accuracy of the baseline by uploading only about 1% model parameters, for a compression ratio of $32$ of the autoencoder. Expand
Learning to Learn to Demodulate with Uncertainty Quantification via Bayesian Meta-Learning
TLDR
Numerical results for singleinput single-output Rayleigh fading channels with transmitter’s non-linearities are provided that compare symbol error rate and expected calibration error for both frequentist and Bayesian meta-learning, illustrating how the latter is both more accurate and better-calibrated. Expand
Black-Box and Modular Meta-Learning for Power Control via Random Edge Graph Neural Networks
TLDR
Numerical results validate the benefits of meta-learning for power control problems over joint training schemes, and demonstrate the advantages of modular meta- learning when data availability is extremely limited. Expand
Sharing to learn and learning to share - Fitting together Meta-Learning, Multi-Task Learning, and Transfer Learning : A meta review
TLDR
This work delivers a literature review of the articles, which fuses two algorithms to accomplish multiple tasks, and introduces a global generic learning network, an ensemble of meta learning, transfer learning, and multi-task learning. Expand
...
1
2
...

References

SHOWING 1-10 OF 49 REFERENCES
Deep Learning Enabled Optimization of Downlink Beamforming Under Per-Antenna Power Constraints: Algorithms and Experimental Demonstration
TLDR
This paper studies fast downlink beamforming algorithms using deep learning in multiuser multiple-input-single-output systems where each transmit antenna at the base station has its own power constraint and proposes a deep neural network structure to learn the optimal beamforming based on convolutional networks. Expand
Unsupervised Learning-Based Fast Beamforming Design for Downlink MIMO
TLDR
A fast beamforming design method using unsupervised learning, which trains the deep neural network (DNN) offline and provides real-time service online only with simple neural network operations, which reduces the computational complexity and volume of the DNN, making it more suitable for low computation-capacity devices. Expand
A Deep Learning Framework for Optimization of MISO Downlink Beamforming
TLDR
A deep learning framework for the optimization of downlink beamforming is proposed based on convolutional neural networks and exploitation of expert knowledge, such as the uplink-downlink duality and the known structure of optimal solutions, paving the way for fast realization of optimal beamforming in multiuser MISO systems. Expand
Online and Offline Deep Learning Strategies For Channel Estimation and Hybrid Beamforming in Multi-Carrier mm-Wave Massive MIMO Systems.
TLDR
This paper considers a massive MIMO Orthogonal Frequency Division Multiplexing (MIMO-OFDM) system and proposes three different DL frameworks comprising convolutional neural networks (CNNs), which accept the received pilot signal as input and yield the hybrid beamformers at the output. Expand
Deep Learning Strategies For Joint Channel Estimation and Hybrid Beamforming in Multi-Carrier mm-Wave Massive MIMO Systems
TLDR
This paper considers a massive MIMO Orthogonal Frequency Division Multiplexing (MIMO-OFDM) system and proposes three different DL frameworks comprising convolutional neural networks (CNNs), which accept the received pilot signal as input and yield the hybrid beamformers at the output. Expand
Learning to optimize: Training deep neural networks for wireless resource management
TLDR
This work first characterize a class of ‘learnable algorithms’ and then design DNNs to approximate some algorithms of interest in wireless communications, demonstrating the superior ability ofDNNs for approximating two considerably complex algorithms that are designed for power allocation in wireless transmit signal design, while giving orders of magnitude speedup in computational time. Expand
Transfer Learning for Mixed-Integer Resource Allocation Problems in Wireless Networks
TLDR
A transfer learning method via self-imitation, based on a general “learning to optimize” framework for solving MINLP problems, that can tackle the task mismatch issue with a few additional unlabeled training samples, which is especially important when transferring to large-size problems. Expand
Meta-Learning to Communicate: Fast End-to-End Training for Fading Channels
TLDR
Rather than training a common model for all channels, meta-learning finds a common initialization vector that enables fast training on any channel, demonstrating significant training speed-ups and validated via numerical results. Expand
Towards Optimal Power Control via Ensembling Deep Neural Networks
TLDR
Simulation results show that for the standard symmetric $K$ -user Gaussian interference channel, the proposed methods can outperform state-of-the-art power control solutions under a variety of system configurations. Expand
Power of Deep Learning for Channel Estimation and Signal Detection in OFDM Systems
TLDR
The proposed deep learning-based approach to handle wireless OFDM channels in an end-to-end manner is more robust than conventional methods when fewer training pilots are used, the cyclic prefix is omitted, and nonlinear clipping noise exists. Expand
...
1
2
3
4
5
...