arXiv subjects

Yifei Shen

Publications and source records attributed to Yifei Shen.

78 records · Page 5Linked to original sources

arXiv2019

A Graph Neural Network Approach for Scalable Wireless Power Control

Deep neural networks have recently emerged as a disruptive technology to solve NP-hard wireless resource allocation problems in a real-time manner. However, the adopted neural network structures, e.g., multi-layer perceptron (MLP) and convolutional neural network (CNN), are inherited from deep learning for image processing tasks, and thus are not tailored to problems in wireless networks. In particular, the performance of these methods deteriorates dramatically when the wireless network size becomes large. In this paper, we propose to utilize graph neural networks (GNNs) to develop scalable methods for solving the power control problem in $K$-user interference channels. Specifically, a $K$-user interference channel is first modeled as a complete graph, where the quantitative information of wireless channels is incorporated as the features of the graph. We then propose an interference graph convolutional neural network (IGCNet) to learn the optimal power control in an unsupervised manner. It is shown that one-layer IGCNet is a universal approximator to continuous set functions, which well matches the permutation invariance property of interference channels and it is robust to imperfect channel state information (CSI). Extensive simulations will show that the proposed IGCNet outperforms existing methods and achieves significant speedup over the classic algorithm for power control, namely, WMMSE. The code is available on https://github.com/yshenaw/Globecom2019.

cs.IT↗

arXiv2019

Polar Codes with Memory

Polar codes with memory (PCM) are proposed in this paper: a pair of consecutive code blocks containing a controlled number of mutual information bits. The shared mutual information bits of the succeeded block can help the failed block to recover. The underlying polar codes can employ any decoding scheme such as the successive cancellation (SC) decoding (PCM-SC), the belief propagation (BP) decoding (PCM-BP), and the successive cancellation list (SCL) decoding (PCM-SCL). The analysis shows that the packet error rate (PER) of PCM decreases to the order of PER squared while maintaining the same complexity as the underlying polar codes. Simulation results indicate that for PCM-SC, the PER is comparable to (less than 0.3 dB) the stand-alone SCL decoding with two lists for the block length $N=256$. The PER of PCM-SCL with $L$ lists can match that of the stand-alone SCL decoding with $2L$ lists. Two hardware decoders for PCM are also implemented: the in-serial (IS) decoder and the low-latency interleaved (LLI) decoder. For $N=256$, synthesis results show that in the worst case, the latency of the PCM LLI decoder is only $16.1\%$ of the adaptive SCL decoder with $L=2$, while the throughput is improved by 13 times compared to it.

cs.IT↗

arXiv2019

LORM: Learning to Optimize for Resource Management in Wireless Networks with Few Training Samples

Effective resource management plays a pivotal role in wireless networks, which, unfortunately, results in challenging mixed-integer nonlinear programming (MINLP) problems in most cases. Machine learning-based methods have recently emerged as a disruptive way to obtain near-optimal performance for MINLPs with affordable computational complexity. There have been some attempts in applying such methods to resource management in wireless networks, but these attempts require huge amounts of training samples and lack the capability to handle constrained problems. Furthermore, they suffer from severe performance deterioration when the network parameters change, which commonly happens and is referred to as the task mismatch problem. In this paper, to reduce the sample complexity and address the feasibility issue, we propose a framework of Learning to Optimize for Resource Management (LORM). Instead of the end-to-end learning approach adopted in previous studies, LORM learns the optimal pruning policy in the branch-and-bound algorithm for MINLPs via a sample-efficient method, namely, imitation learning. To further address the task mismatch problem, we develop a transfer learning method via self-imitation in LORM, named LORM-TL, which can quickly adapt a pre-trained machine learning model to the new task with only a few additional unlabeled training samples. Numerical simulations will demonstrate that LORM outperforms specialized state-of-the-art algorithms and achieves near-optimal performance, while achieving significant speedup compared with the branch-and-bound algorithm. Moreover, LORM-TL, by relying on a few unlabeled samples, achieves comparable performance with the model trained from scratch with sufficient labeled samples.

eess.SP↗

arXiv2018

Transfer Learning for Mixed-Integer Resource Allocation Problems in Wireless Networks

Effective resource allocation plays a pivotal role for performance optimization in wireless networks. Unfortunately, typical resource allocation problems are mixed-integer nonlinear programming (MINLP) problems, which are NP-hard. Machine learning based methods recently emerge as a disruptive way to obtain near-optimal performance for MINLP problems with affordable computational complexity. However, they suffer from severe performance deterioration when the network parameters change, which commonly happens in practice and can be characterized as the task mismatch issue. In this paper, we propose a transfer learning method via self-imitation, to address this issue for effective resource allocation in wireless networks. It is based on a general "learning to optimize" framework for solving MINLP problems. A unique advantage of the proposed method is that it can tackle the task mismatch issue with a few additional unlabeled training samples, which is especially important when transferring to large-size problems. Numerical experiments demonstrate that with much less training time, the proposed method achieves comparable performance with the model trained from scratch with sufficient amount of labeled samples. To the best of our knowledge, this is the first work that applies transfer learning for resource allocation in wireless networks.

eess.SP↗

arXiv2018

Scalable network adaptation for Cloud-RANs: An imitation learning approach

Network adaptation is essential for the efficient operation of Cloud-RANs. Unfortunately, it leads to highly intractable mixed-integer nonlinear programming problems. Existing solutions typically rely on convex relaxation, which yield performance gaps that are difficult to quantify. Meanwhile, global optimization algorithms such as branch-and-bound can find optimal solutions but with prohibitive computational complexity. In this paper, to obtain near-optimal solutions at affordable complexity, we propose to approximate the branch-and-bound algorithm via machine learning. Specifically, the pruning procedure in branch-and-bound is formulated as a sequential decision problem, followed by learning the oracle's action via imitation learning. A unique advantage of this framework is that the training process only requires a small dataset, and it is scalable to problem instances with larger dimensions than the training setting. This is achieved by identifying and leveraging the problem-size independent features. Numerical simulations demonstrate that the learning based framework significantly outperforms competing methods, with computational complexity much lower than the traditional branch-and-bound algorithm.

eess.SP↗

arXiv2018

Comparing large-scale graphs based on quantum probability theory

In this paper, a new measurement to compare two large-scale graphs based on the theory of quantum probability is proposed. An explicit form for the spectral distribution of the corresponding adjacency matrix of a graph is established. Our proposed distance between two graphs is defined as the distance between the corresponding moment matrices of their spectral distributions. It is shown that the spectral distributions of their adjacency matrices in a vector state includes information not only about their eigenvalues, but also about the corresponding eigenvectors. Moreover, we prove that such distance is graph invariant and sub-structure invariant. Examples with various graphs are given, and distances between graphs with few vertices are checked. Computational results for real large-scale networks show that its accuracy is better than any existing methods and time cost is extensively cheap.

cs.DM↗