Y
Yifei Shen
Researcher at Hong Kong University of Science and Technology
Publications - 38
Citations - 535
Yifei Shen is an academic researcher from Hong Kong University of Science and Technology. The author has contributed to research in topics: Computer science & Wireless network. The author has an hindex of 7, co-authored 31 publications receiving 246 citations. Previous affiliations of Yifei Shen include ShanghaiTech University.
Papers
More filters
Journal ArticleDOI
Graph Neural Networks for Scalable Radio Resource Management: Architecture Design and Theoretical Analysis
TL;DR: In this paper, a message passing graph neural network (MPGNN) was proposed to solve large-scale radio resource management problems in wireless networks, which can solve the beamforming problem in an interference channel with 1000 transceiver pairs within 6 milliseconds on a single GPU.
Posted Content
Graph Neural Networks for Scalable Radio Resource Management: Architecture Design and Theoretical Analysis
TL;DR: This paper demonstrates that radio resource management problems can be formulated as graph optimization problems that enjoy a universal permutation equivariance property, and identifies a family of neural networks, named message passing graph neural networks (MPGNNs), which can generalize to large-scale problems, while enjoying a high computational efficiency.
Journal ArticleDOI
LORM: Learning to Optimize for Resource Management in Wireless Networks With Few Training Samples
TL;DR: Li et al. as mentioned in this paper proposed a framework of Learning to Optimize for Resource Management (LORM), which learns the optimal pruning policy in the branch-and-bound algorithm for mixed-integer nonlinear programming (MINLPs) via a sampleefficient method, namely, imitation learning.
Proceedings ArticleDOI
A Graph Neural Network Approach for Scalable Wireless Power Control
TL;DR: In this paper, an interference graph convolutional neural network (IGCNet) is proposed to learn the optimal power control in an unsupervised manner, which is a universal approximation to continuous set functions.
Posted Content
LORM: Learning to Optimize for Resource Management in Wireless Networks with Few Training Samples
TL;DR: A transfer learning method via self-imitation in LORM can quickly adapt a pre-trained machine learning model to the new task with only a few additional unlabeled training samples, and achieves comparable performance with the model trained from scratch with sufficient labeled samples.