Search

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. © 2019 IEEE.

Effective resource allocation plays a pivotal role 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 the proposed method, with much less training time, achieves comparable performance with the model trained from scratch based on sufficient labeled samples. To the best of our knowledge, this is the first work that applies transfer learning for resource allocation in wireless networks. © 2019 IEEE.

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 the proposed 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 graphs show that its accuracy is better than any existing methods and time cost is extensively cheap. © 2019 Elsevier Inc.

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. © 2018 IEEE.

Effective resource allocation plays a pivotal role 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 the proposed method, with much less training time, achieves comparable performance with the model trained from scratch based on sufficient labeled samples. To the best of our knowledge, this is the first work that applies transfer learning for resource allocation in wireless networks.

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.

Hybrids are used extensively in agriculture due to their superior performance in seed yield and plant growth, yet the molecular mechanisms underpinning hybrid performance are not well understood. Recent evidence has suggested that a decrease in basal defense response gene expression regulated by reduced levels of salicylic acid (SA) may be important for vigor in certain hybrid combinations. Decreasing levels of SA in the Arabidopsis (Arabidopsis thaliana) accession C24 through the introduction of the SA catabolic enzyme salicylate1 hydroxylase (NahG) increases plant size, phenocopying the large-sized C24/Landsberg erecta (Ler) F1 hybrids. C24♀ × Ler♂ F1 hybrids and C24 NahG lines shared differentially expressed genes and pathways associated with plant defense and leaf senescence including decreased expression of SA biosynthetic genes and SA response genes. The expression of TL1 BINDING TRANSCRIPTION FACTOR1, a key regulator in resource allocation between growth and defense, was decreased in both the F1 hybrid and the C24 NahG lines, which may promote growth. Both C24 NahG lines and the F1 hybrids showed decreased expression of the key senescence-associated transcription factors WRKY53, NAC-CONTAINING PROTEIN29, and ORESARA1 with a delayed onset of senescence compared to C24 plants. The delay in senescence resulted in an extension of the photosynthetic period in the leaves of F1 hybrids compared to the parental lines, potentially allowing each leaf to contribute more resources toward growth. Hybrid vigor describes the superior performance of hybrid crop plants relative to their parents in important agronomic traits such as biomass and seed yield (reviewed by Chen, 2013). Hybrids in maize (Zea mays), rice (Oryza sativa), and canola (Brassica napus) have increased seed yield and are used extensively in agriculture. Hybrid vigor is associated with alterations in gene expression profiles resulting from interactions between the two parental genomes present in the one nucl

Similar to existing codes, puncturing and shortening are two general ways to obtain an arbitrary code length and code rate for polar codes. When some of the coded bits are punctured or shortened, it is equivalent to a situation in which the underlying channels of the polar codes are different. Therefore, the quality of bit channels with puncturing or shortening differ from the original qualities, which can greatly affect the construction of polar codes. In this paper, a general construction of polar codes is studied in two aspects: 1) the theoretical foundation of the construction; and 2) the hardware implementation of polar codes encoders. In contrast to the original identical and independent binary-input, memoryless, symmetric (BMS) channels, these underlying BMS channels can be different. For binary erasure channel (BEC) channels, recursive equations can be employed assuming independent BMS channels. For all other channel types, the proposed general construction of polar codes is based on the existing Tal-Vardy's procedure. The symmetric property and the degradation relationship are shown to be preserved under the general setting, rendering the possibility of a modification of Tal-Vardy's procedure. Simulation results clearly show improved error performance with re-ordering using the proposed new procedures. In terms of hardware, a novel pruned folded encoder architecture is proposed which saves the computation for the beginning frozen bits. Implementation results show the pruned encoder achieve 28% throughput improvement., Comment: Polar Codes,General Construction,Puncture,Shorten