提高学习效率对于使用高度动态环境的无线通信中的深度神经网络（DNN）来学习资源分配至关重要。将域名知识纳入学习是处理此问题的有希望的方式，这是无线社区中的新兴主题。在本文中，我们首先简要概述了使用域知识的两种方法：引入数学模型或先前的知识来深入学习。然后，我们考虑一种关于无线任务中广泛存在的对称性的置换性价比。为了解释这种通用的先前如何利用，以提高学习效率，我们采取排名，共同对DNN的输入和输出共同排序。我们在子载波之间使用电力分配，概率的内容缓存和干扰协调，以说明通过利用属性来提高学习效率。从案例研究中，我们发现所需的训练样本实现给定的系统性能随着诸如有趣现象的子载波或内容的数量而降低：“样品硬化”。仿真结果表明，通过利用先验知识可以显着降低DNN中的训练样本，DNN中的自由参数和训练时间。排名后培训DNN所需的样本可以减少15美元\ SIM 2,400 $折叠，以在不使用之前的情况下实现与对应物相同的系统性能。

Learning precoding policies with neural networks enables low complexity online implementation, robustness to channel impairments, and joint optimization with channel acquisition. However, existing neural networks suffer from high training complexity and poor generalization ability when they are used to learn to optimize precoding for mitigating multi-user interference. This impedes their use in practical systems where the number of users is time-varying. In this paper, we propose a graph neural network (GNN) to learn precoding policies by harnessing both the mathematical model and the property of the policies. We first show that a vanilla GNN cannot well-learn pseudo-inverse of channel matrix when the numbers of antennas and users are large, and is not generalizable to unseen numbers of users. Then, we design a GNN by resorting to the Taylor's expansion of matrix pseudo-inverse, which allows for capturing the importance of the neighbored edges to be aggregated that is crucial for learning precoding policies efficiently. Simulation results show that the proposed GNN can well learn spectral efficient and energy efficient precoding policies in single- and multi-cell multi-user multi-antenna systems with low training complexity, and can be well generalized to the numbers of users.

由于处理非covex公式的能力，深入研究深度学习（DL）技术以优化多用户多输入单输出（MU-MISO）下行链接系统。但是，现有的深神经网络（DNN）的固定计算结构在系统大小（即天线或用户的数量）方面缺乏灵活性。本文开发了一个双方图神经网络（BGNN）框架，这是一种可扩展的DL溶液，旨在多端纳纳波束形成优化。首先，MU-MISO系统以两分图为特征，其中两个不相交的顶点集（由传输天线和用户组成）通过成对边缘连接。这些顶点互连状态是通过通道褪色系数建模的。因此，将通用的光束优化过程解释为重量双分图上的计算任务。这种方法将波束成型的优化过程分为多个用于单个天线顶点和用户顶点的子操作。分离的顶点操作导致可扩展的光束成型计算，这些计算不变到系统大小。顶点操作是由一组DNN模块实现的，这些DNN模块共同构成了BGNN体系结构。在所有天线和用户中都重复使用相同的DNN，以使所得的学习结构变得灵活地适合网络大小。 BGNN的组件DNN在许多具有随机变化的网络尺寸的MU-MISO配置上进行了训练。结果，训练有素的BGNN可以普遍应用于任意的MU-MISO系统。数值结果验证了BGNN框架比常规方法的优势。

Integrated space-air-ground networks promise to offer a valuable solution space for empowering the sixth generation of communication networks (6G), particularly in the context of connecting the unconnected and ultraconnecting the connected. Such digital inclusion thrive makes resource management problems, especially those accounting for load-balancing considerations, of particular interest. The conventional model-based optimization methods, however, often fail to meet the real-time processing and quality-of-service needs, due to the high heterogeneity of the space-air-ground networks, and the typical complexity of the classical algorithms. Given the premises of artificial intelligence at automating wireless networks design and the large-scale heterogeneity of non-terrestrial networks, this paper focuses on showcasing the prospects of machine learning in the context of user scheduling in integrated space-air-ground communications. The paper first overviews the most relevant state-of-the art in the context of machine learning applications to the resource allocation problems, with a dedicated attention to space-air-ground networks. The paper then proposes, and shows the benefit of, one specific use case that uses ensembling deep neural networks for optimizing the user scheduling policies in integrated space-high altitude platform station (HAPS)-ground networks. Finally, the paper sheds light on the challenges and open issues that promise to spur the integration of machine learning in space-air-ground networks, namely, online HAPS power adaptation, learning-based channel sensing, data-driven multi-HAPSs resource management, and intelligent flying taxis-empowered systems.

在带有频划分双链体（FDD）的常规多用户多用户多输入多输出（MU-MIMO）系统中，尽管高度耦合，但已单独设计了通道采集和预编码器优化过程。本文研究了下行链路MU-MIMO系统的端到端设计，其中包括试点序列，有限的反馈和预编码。为了解决这个问题，我们提出了一个新颖的深度学习（DL）框架，该框架共同优化了用户的反馈信息生成和基础站（BS）的预编码器设计。 MU-MIMO系统中的每个过程都被智能设计的多个深神经网络（DNN）单元所取代。在BS上，神经网络生成试验序列，并帮助用户获得准确的频道状态信息。在每个用户中，频道反馈操作是由单个用户DNN以分布方式进行的。然后，另一个BS DNN从用户那里收集反馈信息，并确定MIMO预编码矩阵。提出了联合培训算法以端到端的方式优化所有DNN单元。此外，还提出了一种可以避免针对可扩展设计的不同网络大小进行重新训练的培训策略。数值结果证明了与经典优化技术和其他常规DNN方案相比，提出的DL框架的有效性。

在本文中，我们旨在改善干扰限制的无线网络中超级可靠性和低延迟通信（URLLC）的服务质量（QoS）。为了在通道连贯性时间内获得时间多样性，我们首先提出了一个随机重复方案，该方案随机将干扰能力随机。然后，我们优化了每个数据包的保留插槽数量和重复数量，以最大程度地减少QoS违规概率，该概率定义为无法实现URLLC的用户百分比。我们构建了一个级联的随机边缘图神经网络（REGNN），以表示重复方案并开发一种无模型的无监督学习方法来训练它。我们在对称场景中使用随机几何形状分析了QoS违规概率，并应用基于模型的详尽搜索（ES）方法来找到最佳解决方案。仿真结果表明，在对称方案中，通过模型学习方法和基于模型的ES方法实现的QoS违规概率几乎相同。在更一般的情况下，级联的Regnn在具有不同尺度，网络拓扑，细胞密度和频率重复使用因子的无线网络中很好地概括了。在模型不匹配的情况下，它的表现优于基于模型的ES方法。

我们提出了一种数据驱动的电力分配方法，在联邦学习（FL）上的受干扰有限的无线网络中的电力分配。功率策略旨在在通信约束下的流行过程中最大化传输的信息，具有提高全局流动模型的训练精度和效率的最终目标。所提出的功率分配策略使用图形卷积网络进行参数化，并且通过引流 - 双算法解决了相关的约束优化问题。数值实验表明，所提出的方法在传输成功率和流动性能方面优于三种基线方法。

传统上，信号处理，通信和控制一直依赖经典的统计建模技术。这种基于模型的方法利用代表基本物理，先验信息和其他领域知识的数学公式。简单的经典模型有用，但对不准确性敏感，当真实系统显示复杂或动态行为时，可能会导致性能差。另一方面，随着数据集变得丰富，现代深度学习管道的力量增加，纯粹的数据驱动的方法越来越流行。深度神经网络（DNNS）使用通用体系结构，这些架构学会从数据中运行，并表现出出色的性能，尤其是针对受监督的问题。但是，DNN通常需要大量的数据和巨大的计算资源，从而限制了它们对某些信号处理方案的适用性。我们对将原则数学模型与数据驱动系统相结合的混合技术感兴趣，以从两种方法的优势中受益。这种基于模型的深度学习方法通​​过为特定问题设计的数学结构以及从有限的数据中学习来利用这两个部分领域知识。在本文中，我们调查了研究和设计基于模型的深度学习系统的领先方法。我们根据其推理机制将基于混合模型/数据驱动的系统分为类别。我们对以系统的方式将基于模型的算法与深度学习以及具体指南和详细的信号处理示例相结合的领先方法进行了全面综述。我们的目的是促进对未来系统的设计和研究信号处理和机器学习的交集，这些系统结合了两个领域的优势。

Deep learning-based approaches have been developed to solve challenging problems in wireless communications, leading to promising results. Early attempts adopted neural network architectures inherited from applications such as computer vision. They often yield poor performance in large scale networks (i.e., poor scalability) and unseen network settings (i.e., poor generalization). To resolve these issues, graph neural networks (GNNs) have been recently adopted, as they can effectively exploit the domain knowledge, i.e., the graph topology in wireless communications problems. GNN-based methods can achieve near-optimal performance in large-scale networks and generalize well under different system settings, but the theoretical underpinnings and design guidelines remain elusive, which may hinder their practical implementations. This paper endeavors to fill both the theoretical and practical gaps. For theoretical guarantees, we prove that GNNs achieve near-optimal performance in wireless networks with much fewer training samples than traditional neural architectures. Specifically, to solve an optimization problem on an $n$-node graph (where the nodes may represent users, base stations, or antennas), GNNs' generalization error and required number of training samples are $\mathcal{O}(n)$ and $\mathcal{O}(n^2)$ times lower than the unstructured multi-layer perceptrons. For design guidelines, we propose a unified framework that is applicable to general design problems in wireless networks, which includes graph modeling, neural architecture design, and theory-guided performance enhancement. Extensive simulations, which cover a variety of important problems and network settings, verify our theory and the effectiveness of the proposed design framework.

Terahertz频段（0.1---10 THZ）中的无线通信被视为未来第六代（6G）无线通信系统的关键促进技术之一，超出了大量多重输入多重输出（大量MIMO）技术。但是，THZ频率的非常高的传播衰减和分子吸收通常限制了信号传输距离和覆盖范围。从最近在可重构智能表面（RIS）上实现智能无线电传播环境的突破，我们为多跳RIS RIS辅助通信网络提供了一种新型的混合波束形成方案，以改善THZ波段频率的覆盖范围。特别是，部署了多个被动和可控的RIS，以协助基站（BS）和多个单人体用户之间的传输。我们通过利用最新的深钢筋学习（DRL）来应对传播损失的最新进展，研究了BS在BS和RISS上的模拟光束矩阵的联合设计。为了改善拟议的基于DRL的算法的收敛性，然后设计了两种算法，以初始化数字波束形成和使用交替优化技术的模拟波束形成矩阵。仿真结果表明，与基准相比，我们提出的方案能够改善50 \％的THZ通信范围。此外，还表明，我们提出的基于DRL的方法是解决NP-固定光束形成问题的最先进方法，尤其是当RIS辅助THZ通信网络的信号经历多个啤酒花时。

迄今为止，通信系统主要旨在可靠地交流位序列。这种方法提供了有效的工程设计，这些设计对消息的含义或消息交换所旨在实现的目标不可知。但是，下一代系统可以通过将消息语义和沟通目标折叠到其设计中来丰富。此外，可以使这些系统了解进行交流交流的环境，从而为新颖的设计见解提供途径。本教程总结了迄今为止的努力，从早期改编，语义意识和以任务为导向的通信开始，涵盖了基础，算法和潜在的实现。重点是利用信息理论提供基础的方法，以及学习在语义和任务感知通信中的重要作用。

鉴于无线频谱的有限性和对无线通信最近的技术突破产生的频谱使用不断增加的需求，干扰问题仍在继续持续存在。尽管最近解决干涉问题的进步，但干扰仍然呈现出有效使用频谱的挑战。这部分是由于Wi-Fi的无许可和管理共享乐队使用的升高，长期演进（LTE）未许可（LTE-U），LTE许可辅助访问（LAA），5G NR等机会主义频谱访问解决方案。因此，需要对干扰稳健的有效频谱使用方案的需求从未如此重要。在过去，通过使用避免技术以及非AI缓解方法（例如，自适应滤波器）来解决问题的大多数解决方案。非AI技术的关键缺陷是需要提取或开发信号特征的域专业知识，例如CycrationArity，带宽和干扰信号的调制。最近，研究人员已成功探索了AI / ML的物理（PHY）层技术，尤其是深度学习，可减少或补偿干扰信号，而不是简单地避免它。 ML基于ML的方法的潜在思想是学习来自数据的干扰或干扰特性，从而使需要对抑制干扰的域专业知识进行侧联。在本文中，我们审查了广泛的技术，这些技术已经深入了解抑制干扰。我们为干扰抑制中许多不同类型的深度学习技术提供比较和指导。此外，我们突出了在干扰抑制中成功采用深度学习的挑战和潜在的未来研究方向。

Effective and adaptive interference management is required in next generation wireless communication systems. To address this challenge, Rate-Splitting Multiple Access (RSMA), relying on multi-antenna rate-splitting (RS) at the transmitter and successive interference cancellation (SIC) at the receivers, has been intensively studied in recent years, albeit mostly under the assumption of perfect Channel State Information at the Receiver (CSIR) and ideal capacity-achieving modulation and coding schemes. To assess its practical performance, benefits, and limits under more realistic conditions, this work proposes a novel design for a practical RSMA receiver based on model-based deep learning (MBDL) methods, which aims to unite the simple structure of the conventional SIC receiver and the robustness and model agnosticism of deep learning techniques. The MBDL receiver is evaluated in terms of uncoded Symbol Error Rate (SER), throughput performance through Link-Level Simulations (LLS), and average training overhead. Also, a comparison with the SIC receiver, with perfect and imperfect CSIR, is given. Results reveal that the MBDL receiver outperforms by a significant margin the SIC receiver with imperfect CSIR, due to its ability to generate on demand non-linear symbol detection boundaries in a pure data-driven manner.

As an efficient graph analytical tool, graph neural networks (GNNs) have special properties that are particularly fit for the characteristics and requirements of wireless communications, exhibiting good potential for the advancement of next-generation wireless communications. This article aims to provide a comprehensive overview of the interplay between GNNs and wireless communications, including GNNs for wireless communications (GNN4Com) and wireless communications for GNNs (Com4GNN). In particular, we discuss GNN4Com based on how graphical models are constructed and introduce Com4GNN with corresponding incentives. We also highlight potential research directions to promote future research endeavors for GNNs in wireless communications.

从早期图像处理到现代计算成像，成功的模型和算法都依赖于自然信号的基本属性：对称性。在这里，对称是指信号集的不变性属性，例如翻译，旋转或缩放等转换。对称性也可以以模棱两可的形式纳入深度神经网络中，从而可以进行更多的数据效率学习。虽然近年来端到端的图像分类网络的设计方面取得了重要进展，但计算成像引入了对等效网络解决方案的独特挑战，因为我们通常只通过一些嘈杂的不良反向操作员观察图像，可能不是均等的。我们回顾了现象成像的新兴领域，并展示它如何提供改进的概括和新成像机会。在此过程中，我们展示了采集物理学与小组动作之间的相互作用，以及与迭代重建，盲目的压缩感应和自我监督学习之间的联系。

在本文中，提出了用于文本数据传输的语义通信框架。在研究的模型中，基站（BS）从文本数据中提取语义信息，并将其传输到每个用户。语义信息由由一组语义三元组组成的知识图（kg）建模。收到语义信息后，每个用户都使用图形到文本生成模型恢复原始文本。为了衡量所考虑的语义通信框架的性能，提出了共同捕获恢复文本的语义准确性和完整性的语义相似性（MSS）的指标。由于无线资源限制，BS可能无法将整个语义信息传输给每个用户并满足传输延迟约束。因此，BS必须为每个用户选择适当的资源块，并确定和将一部分语义信息传输给用户。因此，我们制定了一个优化问题，其目标是通过共同优化资源分配策略并确定要传输的部分语义信息来最大化总MSS。为了解决这个问题，提出了与注意力网络集成的基于近端优化的强化增强学习（RL）算法。所提出的算法可以使用注意网络在语义信息中评估每个三重组的重要性，然后在语义信息中三元组的重要性分布与总MSS之间建立关系。与传统的RL算法相比，所提出的算法可以动态调整其学习率，从而确保收敛到本地最佳解决方案。

Recent technological advancements in space, air and ground components have made possible a new network paradigm called "space-air-ground integrated network" (SAGIN). Unmanned aerial vehicles (UAVs) play a key role in SAGINs. However, due to UAVs' high dynamics and complexity, the real-world deployment of a SAGIN becomes a major barrier for realizing such SAGINs. Compared to the space and terrestrial components, UAVs are expected to meet performance requirements with high flexibility and dynamics using limited resources. Therefore, employing UAVs in various usage scenarios requires well-designed planning in algorithmic approaches. In this paper, we provide a comprehensive review of recent learning-based algorithmic approaches. We consider possible reward functions and discuss the state-of-the-art algorithms for optimizing the reward functions, including Q-learning, deep Q-learning, multi-armed bandit (MAB), particle swarm optimization (PSO) and satisfaction-based learning algorithms. Unlike other survey papers, we focus on the methodological perspective of the optimization problem, which can be applicable to various UAV-assisted missions on a SAGIN using these algorithms. We simulate users and environments according to real-world scenarios and compare the learning-based and PSO-based methods in terms of throughput, load, fairness, computation time, etc. We also implement and evaluate the 2-dimensional (2D) and 3-dimensional (3D) variations of these algorithms to reflect different deployment cases. Our simulation suggests that the $3$D satisfaction-based learning algorithm outperforms the other approaches for various metrics in most cases. We discuss some open challenges at the end and our findings aim to provide design guidelines for algorithm selections while optimizing the deployment of UAV-assisted SAGINs.

Deep neural networks (DNNs) are currently widely used for many artificial intelligence (AI) applications including computer vision, speech recognition, and robotics. While DNNs deliver state-of-the-art accuracy on many AI tasks, it comes at the cost of high computational complexity. Accordingly, techniques that enable efficient processing of DNNs to improve energy efficiency and throughput without sacrificing application accuracy or increasing hardware cost are critical to the wide deployment of DNNs in AI systems.This article aims to provide a comprehensive tutorial and survey about the recent advances towards the goal of enabling efficient processing of DNNs. Specifically, it will provide an overview of DNNs, discuss various hardware platforms and architectures that support DNNs, and highlight key trends in reducing the computation cost of DNNs either solely via hardware design changes or via joint hardware design and DNN algorithm changes. It will also summarize various development resources that enable researchers and practitioners to quickly get started in this field, and highlight important benchmarking metrics and design considerations that should be used for evaluating the rapidly growing number of DNN hardware designs, optionally including algorithmic co-designs, being proposed in academia and industry.The reader will take away the following concepts from this article: understand the key design considerations for DNNs; be able to evaluate different DNN hardware implementations with benchmarks and comparison metrics; understand the trade-offs between various hardware architectures and platforms; be able to evaluate the utility of various DNN design techniques for efficient processing; and understand recent implementation trends and opportunities.

In this tutorial paper, we look into the evolution and prospect of network architecture and propose a novel conceptual architecture for the 6th generation (6G) networks. The proposed architecture has two key elements, i.e., holistic network virtualization and pervasive artificial intelligence (AI). The holistic network virtualization consists of network slicing and digital twin, from the aspects of service provision and service demand, respectively, to incorporate service-centric and user-centric networking. The pervasive network intelligence integrates AI into future networks from the perspectives of networking for AI and AI for networking, respectively. Building on holistic network virtualization and pervasive network intelligence, the proposed architecture can facilitate three types of interplay, i.e., the interplay between digital twin and network slicing paradigms, between model-driven and data-driven methods for network management, and between virtualization and AI, to maximize the flexibility, scalability, adaptivity, and intelligence for 6G networks. We also identify challenges and open issues related to the proposed architecture. By providing our vision, we aim to inspire further discussions and developments on the potential architecture of 6G.

机器学习在解决无线干扰管理问题方面取得了成功。已经培训了不同种类的深神经网络（DNN），以完成功率控制，波束成形和准入控制等关键任务。基于DNNS的干扰管理模型有两个流行的培训范式：监督学习（即，由优化算法产生的拟合标签）和无监督的学习（即，直接优化一些系统性能测量）。虽然这两种范式都在实践中广泛应用，但由于对这些方法缺乏任何理论理解，但目前尚不清楚如何系统地理解和比较他们的性能。在这项工作中，我们开展理论研究，为这两个训练范例提供了一些深入的了解。首先，我们展示了一些令人惊讶的结果，即对于一些特殊的功率控制问题，无监督的学习可以表现比监督对手更糟糕，因为它更有可能陷入一些低质量的本地解决方案。然后，我们提供了一系列理论结果，以进一步了解两种方法的性质。一般来说，我们表明，当有高质量的标签可用时，监督学习不太可能陷入解决方案，而不是无监督的对应物。此外，我们开发了一种半监督的学习方法，可以妥善整合这两个训练范例，可以有效地利用有限数量的标签来找到高质量的解决方案。为了我们的知识，这些是第一种在基于学习的无线通信系统设计中了解不同培训方法的第一组理论结果。