Communication efficiency is of importance for wireless federated learning systems. In this paper, we propose a communication-efficient strategy for federated learning over multiple-input multiple-output (MIMO) multiple access channels (MACs). The proposed strategy comprises two components. When sending a locally computed gradient, each device compresses a high dimensional local gradient to multiple lower-dimensional gradient vectors using block sparsification. When receiving a superposition of the compressed local gradients via a MIMO-MAC, a parameter server (PS) performs a joint MIMO detection and the sparse local-gradient recovery. Inspired by the turbo decoding principle, our joint detection-and-recovery algorithm accurately recovers the high-dimensional local gradients by iteratively exchanging their beliefs for MIMO detection and sparse local gradient recovery outputs. We then analyze the reconstruction error of the proposed algorithm and its impact on the convergence rate of federated learning. From simulations, our gradient compression and joint detection-and-recovery methods diminish the communication cost significantly while achieving identical classification accuracy for the case without any compression.
We provide the optimal receive combining strategy for federated learning in multiple-input multiple-output (MIMO) systems. Our proposed algorithm allows the clients to perform individual gradient sparsification which greatly improves performance in scenarios with heterogeneous (non i.i.d.) training data. The proposed method beats the benchmark by a wide margin.
We propose a novel uplink communication method, coined random orthogonalization, for federated learning (FL) in a massive multiple-input and multiple-output (MIMO) wireless system. The key novelty of random orthogonalization comes from the tight coupling of FL model aggregation and two unique characteristics of massive MIMO - channel hardening and favorable propagation. As a result, random orthogonalization can achieve natural over-the-air model aggregation without requiring transmitter side channel state information, while significantly reducing the channel estimation overhead at the receiver…
While 5G networks are being rolled out, the definition of the potential 5G-Advanced features and the identification of disruptive technologies for 6G systems are being addressed by the scientific and academic communities to tackle the challenges that 2030 communication systems will face, such as terabit-capacity and always-on networks. In this framework, it is globally recognised that Non-Terrestrial Networks (NTN) will play a fundamental role in support to a fully connected world, in which physical, human, and digital domains will converge. In this framework, one of the main challenges that N…
United States CCDC Army Research Laboratory（美国CCDC陆军研究实验室）
Millimeter wave multiple-input multiple-output (mmWave-MIMO) systems with small number of radio-frequency (RF) chains have limited multiplexing gain. Spatial path index modulation (SPIM) is helpful in improving this gain by utilizing additional signal bits modulated by the indices of spatial paths. In this paper, we introduce model-based and model-free frameworks for beamformer design in multi-user SPIM-MIMO systems. We first design the beamformers via model-based manifold optimization algorithm. Then, we leverage federated learning (FL) with dropout learning (DL) to train a learning model on …
University of Virginia（弗吉尼亚大学）；The Pennsylvania State University（宾夕法尼亚州立大学）；Princeton University（普林斯顿大学）
We propose a novel communication design, termed random orthogonalization, for federated learning (FL) in a massive multiple-input and multiple-output (MIMO) wireless system. The key novelty of random orthogonalization comes from the tight coupling of FL and two unique characteristics of massive MIMO -- channel hardening and favorable propagation. As a result, random orthogonalization can achieve natural over-the-air model aggregation without requiring transmitter side channel state information (CSI) for the uplink phase of FL, while significantly reducing the channel estimation overhead at the…
Queen’s University Belfast（贝尔法斯特女王大学）；New York University（纽约大学）
Federated learning (FL) has been considered as a promising learning framework for future machine learning systems due to its privacy preservation and communication efficiency. In beyond-5G/6G systems, it is likely to have multiple FL groups with different learning purposes. This scenario leads to a question: How does a wireless network support multiple FL groups? As an answer, we first propose to use a cell-free massive multiple-input multiple-output (MIMO) network to guarantee the stable operation of multiple FL processes by letting the iterations of these FL processes be executed together wi…
This work proposes novel synchronous, asynchronous, and session-based designs for energy-efficient massive multiple-input multiple-output networks to support federated learning (FL). The synchronous design relies on strict synchronization among users when executing each FL communication round, while the asynchronous design allows more flexibility for users to save energy by using lower computing frequencies. The session-based design splits the downlink and uplink phases in each FL communication round into separate sessions. In this design, we assign users such that one of the participating use…
This paper proposes a novel scheme for cell-free massive multiple-input multiple-output (CFmMIMO) networks to support any federated learning (FL) framework. This scheme allows each instead of all the iterations of the FL framework to happen in a large-scale coherence time to guarantee a stable operation of an FL process. To show how to optimize the FL performance using this proposed scheme, we consider an existing FL framework as an example and target FL training time minimization for this framework. An optimization problem is then formulated to jointly optimize the local accuracy, transmit po…
Machine learning for hybrid beamforming has been extensively studied by using centralized machine learning (CML) techniques, which require the training of a global model with a large dataset collected from the users. However, the transmission of the whole dataset between the users and the base station (BS) is computationally prohibitive due to limited communication bandwidth and privacy concerns. In this work, we introduce a federated learning (FL) based framework for hybrid beamforming, where the model training is performed at the BS by collecting only the gradients from the users. We design …
With its privacy preservation and communication efficiency, federated learning (FL) has emerged as a learning framework that suits beyond 5G and towards 6G systems. This work looks into a future scenario in which there are multiple groups with different learning purposes and participating in different FL processes. We give energy-efficient solutions to demonstrate that this scenario can be realistic. First, to ensure a stable operation of multiple FL processes over wireless channels, we propose to use a massive multiple-input multiple-output network to support the local and global FL training …
Cell-free massive MIMO (CF mMIMO) is a promising next generation wireless architecture to realize federated learning (FL). However, sensitive information of user equipments (UEs) may be exposed to the involved access points or the central processing unit in practice. To guarantee data privacy, effective privacy-preserving mechanisms are defined in this paper. In particular, we demonstrate and characterize the possibility in exploiting the inherent quantization error, caused by low-resolution analog-to-digital converters (ADCs) and digital-to-analog converters (DACs), for privacy-preserving in …
Duzce University（杜兹杰大学）；University of Hertfordshire（赫特福德大学）；Koc University（科奇大学）
Machine learning (ML) has attracted a great research interest for physical layer design problems, such as channel estimation, thanks to its low complexity and robustness. Channel estimation via ML requires model training on a dataset, which usually includes the received pilot signals as input and channel data as output. In previous works, model training is mostly done via centralized learning (CL), where the whole training dataset is collected from the users at the base station (BS). This approach introduces huge communication overhead for data collection. In this paper, to address this challe…
Due to its communication efficiency and privacy-preserving capability, federated learning (FL) has emerged as a promising framework for machine learning in 5G-and-beyond wireless networks. Of great interest is the design and optimization of new wireless network structures that support the stable and fast operation of FL. Cell-free massive multiple-input multiple-output (CFmMIMO) turns out to be a suitable candidate, which allows each communication round in the iterative FL process to be stably executed within a large-scale coherence time. Aiming to reduce the total execution time of the FL pro…
CSI-GPT: Integrating Generative Pre-Trained Transformer with Federated-Tuning to Acquire Downlink Massive MIMO Channels
School of Information and Electronics, Beijing Institute of Technology（北京理工大学信息与电子学院）；King Abdulaziz University（阿卜杜勒阿齐兹国王大学）；School of Electronics and Computer Science, University of Southampton（南安普顿大学电子与计算机科学学院）；Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)（穆罕默德·本·扎耶德人工智能大学）
This paper considers the application of multiple-input multiple-output (MIMO) techniques to non-orthogonal multiple access (NOMA) systems. A new design of precoding and detection matrices for MIMO-NOMA is proposed and its performance is analyzed for the case with a fixed set of power allocation coefficients. To further improve the performance gap between MIMO-NOMA and conventional orthogonal multiple access schemes, user pairing is applied to NOMA and its impact on the system performance is characterized. More sophisticated choices of power allocation coefficients are also proposed to meet var…
We present a novel access protocol for crowd scenarios in massive MIMO (Multiple-input multiple-output) systems. Crowd scenarios are characterized by a large number of users with intermittent access behavior, whereby orthogonal scheduling is infeasible. In such scenarios, random access is a natural choice. The proposed access protocol relies on two essential properties of a massive MIMO system, namely asymptotic orthogonality between user channels and asymptotic invariance of channel powers. Signal processing techniques that take advantage of these properties allow us to view a set of contamin…
We consider an extension of the massive unsourced random access originally proposed by Polyanskiy to the case where the receiver has a very large number of antennas (a massive MIMO base station) and no channel state information is given to the receiver (fully non-coherent detection). Our coding approach borrows the concatenated coding idea from Amalladinne et. al., combined with a novel non-Bayesian `activity detection' algorithm for massive MIMO random access channels, that outperforms currently proposed Bayesian vector AMP (VAMP) schemes currently proposed for activity detection, and does no…
This paper develops a novel approach to obtaining the optimal scheduling strategy in a multi-input multi-output (MIMO) multi-access channel (MAC), where each transmitter is powered by an individual energy harvesting process. Relying on the state-of-the-art convex optimization tools, the proposed approach provides a low-complexity block coordinate ascent algorithm to obtain the optimal transmission policy that maximizes the weighted sum-throughput for MIMO MAC. The proposed approach can provide the optimal benchmarks for all practical schemes in energy-harvesting powered MIMO MAC transmissions.…
Massive MIMO opens up new avenues for enabling highly efficient random access (RA) by offering abundance of spatial degrees of freedom. In this paper, we investigate the grant-free RA with massive MIMO and derive the analytic expressions of success probability of the grant-free RA for conjugate beamforming and zero-forcing beamforming techniques.With the derived analytic expressions, we further shed light on the impact of system parameters on the success probability. Simulation results verify the accuracy of the analyses. It is confirmed that the grant-free RA with massive MIMO is an attractiv…
In this paper, we study the multiple-antenna wireless communication networks, where a large number of devices simultaneously communicate with an access point. The capacity region of multiple-input multiple-output massive multiple access channels (MIMO mMAC) is investigated. While joint typicality decoding is utilized to establish the achievability of capacity region for conventional MAC with fixed number of users, the technique is not directly applicable for MIMO mMAC. Instead, an information-theoretic approach based on Gallager's error exponent analysis is exploited to characterize the \textc…
In this work, the Multiple transmit antennas Multiple Access Channel is considered. A construction of a family of distributed space-time codes for this channel is proposed. No Channel Side Information at the transmitters is assumed and users are not allowed to cooperate together. It is shown that the proposed code achieves the Diversity Multiplexing Tradeoff of the channel. As an example, we consider the two-user MIMO-MAC channel. Simulation results show the significant gain offered by the new coding scheme compared to an orthogonal transmission scheme, e.g. time sharing.
Massive MIMO systems, where the base stations are equipped with hundreds of antenna elements, are an attractive way to attain unprecedented spectral efficiency in future wireless networks. In the "classical" massive MIMO setting, the terminals are assumed fully loaded and a main impairment to the performance comes from the inter-cell pilot contamination, i.e., interference from terminals in neighboring cells using the same pilots as in the home cell. However, when the terminals are active intermittently, it is viable to avoid inter-cell contamination by pre-allocation of pilots, while same-cel…
Wireless networks with many antennas at the base stations and multiplexing of many users, known as Massive MIMO systems, are key to handle the rapid growth of data traffic. As the number of users increases, the random access in contemporary networks will be flooded by user collisions. In this paper, we propose a reengineered random access protocol, coined strongest-user collision resolution (SUCR). It exploits the channel hardening feature of Massive MIMO channels to enable each user to detect collisions, determine how strong the contenders' channels are, and only keep transmitting if it has t…
We establish the optimal diversity-multiplexing (DM) tradeoff for coherent selective-fading multiple-access MIMO channels and provide corresponding code design criteria. As a byproduct, on the conceptual level, we find an interesting relation between the DM tradeoff framework and the notion of dominant error event regions, first introduced in the AWGN case by Gallager, IEEE Trans. IT, 1985. This relation allows us to accurately characterize the error mechanisms in MIMO fading multiple-access channels. In particular, we find that, for a given rate tuple, the maximum achievable diversity order i…
Massive MIMO systems, where the base stations are equipped with hundreds of antennas, are an attractive way to handle the rapid growth of data traffic. As the number of users increases, the initial access and handover in contemporary networks will be flooded by user collisions. In this work, we propose a random access procedure that resolves collisions and also performs timing, channel, and power estimation by simply utilizing the large number of antennas envisioned in massive MIMO systems and the inherent timing misalignments of uplink signals during network access and handover. Numerical res…
In this paper, we investigate the design of linear precoders for the multiple-input multiple-output (MIMO) multiple access channel (MAC). We assume that statistical channel state information (CSI) is available at the transmitters and consider the problem under the practical finite alphabet input assumption. First, we derive an asymptotic (in the large system limit) expression for the weighted sum rate (WSR) of the MIMO MAC with finite alphabet inputs and Weichselberger's MIMO channel model. Subsequently, we obtain the optimal structures of the linear precoders of the users maximizing the asymp…
We consider unsourced random access with MIMO receiver - a crucial communication scenario for future 5G/6G wireless networks. We perform a projection-based decoder analysis and derive energy efficiency achievability bounds when channel state information is unknown at transmitters and the receiver (no-CSI scenario). The comparison to the maximum-likelihood (ML) achievability bounds by Gao et al. (2023) is performed. We show that there is a region where the new bound outperforms the ML bound. The latter fact should not surprise the reader as both decoding criteria are suboptimal when considering…
In this letter, we extend the sparse Kronecker-product (SKP) coding scheme, originally designed for the additive white Gaussian noise (AWGN) channel, to multiple input multiple output (MIMO) unsourced random access (URA). With the SKP coding adopted for MIMO transmission, we develop an efficient Bayesian iterative receiver design to solve the intended challenging trilinear factorization problem. Numerical results show that the proposed design outperforms the existing counterparts, and that it performs well in all simulated settings with various antenna sizes and active-user numbers.
We establish the optimal diversity-multiplexing (DM) tradeoff of coherent selective-fading multiple-access multiple-input multiple-output (MIMO) channels and provide corresponding code design criteria. As a byproduct, on the conceptual level, we find an interesting relation between the DM tradeoff framework and the notion of dominant error event regions which was first introduced in the AWGN case by Gallager, IEEE Trans. IT, 1985. This relation allows to accurately characterize the error mechanisms in MIMO fading multiple-access channels. In particular, we find that, for a given rate tuple, th…
This paper considers sparse device activity detection for cellular machine-type communications with non-orthogonal signatures using the approximate message passing algorithm. This paper compares two network architectures, massive multiple-input multiple-output (MIMO) and cooperative MIMO, in terms of their effectiveness in overcoming inter-cell interference. In the massive MIMO architecture, each base station (BS) detects only the users from its own cell while treating inter-cell interference as noise. In the cooperative MIMO architecture, each BS detects the users from neighboring cells as we…
A massive MIMO system, represented by a base station with hundreds of antennas, is capable of spatially multiplexing many devices and thus naturally suited to serve dense crowds of wireless devices in emerging applications, such as machine-type communications. Crowd scenarios pose new challenges in the pilot-based acquisition of channel state information and call for pilot access protocols that match the intermittent pattern of device activity. A joint pilot assignment and data transmission protocol based on random access is proposed in this paper for the uplink of a massive MIMO system. The p…
In this letter, we investigate the energy efficiency (EE) problem in a millimeter wave (mmWave) massive MIMO (mMIMO) system with non-orthogonal multiple access (NOMA). Multiple two-user clusters are formulated according to their channel correlation and gain difference. Following this, we propose a hybrid analog/digital precoding scheme for the low radio frequency (RF) chains structure at the base station (BS). On this basis, we formulate a power allocation problem aiming to maximize the EE under users' quality of service (QoS) requirements and per-cluster power constraint. An iterative algorit…
Massive access is one of the main use cases of beyond 5G (B5G) wireless networks and massive MIMO is a key technology for supporting it. Prior works studied massive access in the co-located massive MIMO framework. In this paper, we investigate the activity detection in grant-free random access for massive machine type communications (mMTC) in cell-free massive MIMO network. Each active device transmits a pre-assigned non-orthogonal pilot sequence to the APs and the APs send the received signals to a central processing unit (CPU) for joint activity detection. We formulate the maximum likelihood…
Internet of things, supported by machine-to-machine (M2M) communications, is one of the most important applications for future 6th generation (6G) systems. A major challenge facing by 6G is enabling a massive number of M2M devices to access networks in a timely manner. Therefore, this paper exploits the spatial selectivity of massive multi-input multi-output (MIMO) to reduce the collision issue when massive M2M devices initiate random access simultaneously. In particular, a beam-based random access protocol is first proposed to make efficient use of the limited uplink resources for massive M2M…
This paper presents a new approach to intra-cell pilot contamination in crowded massive MIMO scenarios. The approach relies on two essential properties of a massive MIMO system, namely near-orthogonality between user channels and near-stability of channel powers. Signal processing techniques that take advantage of these properties allow us to view a set of contaminated pilot signals as a graph code on which iterative belief propagation can be performed. This makes it possible to decontaminate pilot signals and increase the throughput of the system. The proposed solution exhibits high performan…
Future wireless networks need to support massive machine type communication (mMTC) where a massive number of devices accesses the network and massive MIMO is a promising enabling technology. Massive access schemes have been studied for co-located massive MIMO arrays. In this paper, we investigate the activity detection in grant-free random access for mMTC in cell-free massive MIMO networks using distributed arrays. Each active device transmits a non-orthogonal pilot sequence to the access points (APs) and the APs send the received signals to a central processing unit (CPU) for joint activity d…
We consider cooperative radio access network architectures, especially distributed massive MIMO and Cloud RAN, considering their similarities and differences. We address in particular the major challenge posed to both by the implementation of a high capacity fronthaul network to link the distributed access points to the central processing unit, and consider the effect on uplink performance of quantization of received signals in order to limit fronthaul load. We use the Bussgang decomposition along with a new approach to MMSE estimation of both channel and data to provide the basis of our analy…
Grant-free multiple-input multiple-output (MIMO) usually employs non-orthogonal pilots for joint user detection and channel estimation. However, existing methods are too complex for massive grant-free access in massive MIMO. This letter proposes pilot detection reference signal (PDRS) to greatly reduce the complexity. In PDRS scheme, no iteration is required. Direct weight estimation is also proposed to calculate combining weights without channel estimation. After combining, PDRS recovery errors are used to decide the pilot activity. The simulation results show that the proposed grant-free sch…
The design of highly scalable multiple access schemes is a main challenge in the evolution towards future massive machine-type communications, where reliability and latency constraints must be ensured to a large number of uncoordinated devices. In this scenario, coded random access (CRA) schemes, where successive interference cancellation algorithms allow large improvements with respect to classical random access protocols, have recently attracted an increasing interest. Impressive performance can be potentially obtained by combining CRA with massive multiple input multiple output (MIMO). In t…
Fluid-Antenna-Assisted Distributed Joint Decoding for Cell-Free Massive MIMO Unsourced Random Access
Southeast University（东南大学）；National Mobile Communications Research Laboratory, Frontiers Science Center for Mobile Information Communication and Security, Southeast University（国家移动通信重点实验室，移动信息与安全前沿科学中心，东南大学）；Purple Mountain Laboratories（紫金山实验室）
This paper characterizes the effect of finite rate channel state feedback on the sum rate of a multi-access multiple-input multiple-output (MIMO) system. We propose to control the users jointly, specifically, we first choose the users jointly and then select the corresponding beamforming vectors jointly. To quantify the sum rate, this paper introduces the composite Grassmann manifold and the composite Grassmann matrix. By characterizing the distortion rate function on the composite Grassmann manifold and calculating the logdet function of a random composite Grassmann matrix, a good sum rate ap…
In this paper, we study grant-free random access with massive multiple input multiple output (MIMO) systems. We first show that the performance of massive MIMO based grant-free random access is mainly decided by the probability of preamble collision. The implication of this is that although the number of antennas can be arbitrarily large, the (average) number of successful packet transmissions can be limited by the number of preambles. Then, we propose an approach to preamble collision reduction without increasing the number of preambles using the notion of superpositioned preambles (S-preambl…
To support machine-type communication (MTC), massive multiple-input multiple-output (MIMO) has been considered for grant-free random access. In general, the performance of grant-free random access with massive MIMO is limited by the number of preambles and the number of active devices. In particular, when there are a number of active devices transmitting data packets simultaneously, the signal-to-interference-plus-noise ratio (SINR) cannot be high enough for successful decoding. In this paper, in order to improve performance, we consider immediate re-transmissions for an active device that has…
Grant-free massive access is an important technique for supporting massive machine-type communications (mMTC) for Internet-of-Things (IoT). Two important features in grant-free massive access are low-complexity devices and short-packet data transmission, making the traditional performance metric, achievable rate, unsuitable in this case. In this letter, we investigate grant-free massive access in a massive multiple-input multiple-output (MIMO) system. We consider random access control, and adopt approximate message passing (AMP) for user activity detection and channel estimation in the pilot t…
We investigate the application of non-orthogonal multiple access (NOMA) with successive interference cancellation (SIC) in downlink multiuser multiple-input multiple-output (MIMO) cellular systems, where the total number of receive antennas at user equipment (UE) ends in a cell is more than the number of transmit antennas at the base station (BS). We first dynamically group the UE receive antennas into a number of clusters equal to or more than the number of BS transmit antennas. A single beamforming vector is then shared by all the receive antennas in a cluster. We propose a linear beamformin…
This article considers the massive MIMO unsourced random access problem on a quasi-static Rayleigh fading channel. Given a fixed message length and a prescribed number of channel uses, the objective is to construct a coding scheme that minimizes the energy-per-bit subject to a fixed probability of error. The proposed scheme differs from other state-of-the-art schemes in that it blends activity detection, single-user coding, pilot-aided and temporary decisions-aided iterative channel estimation and decoding, minimum-mean squared error (MMSE) estimation, and successive interference cancellation …
Multiple access is the base for increasing the capacity in multi-user communication networks. However, the growing demand for higher data rates and the number of users who requires communication services has led to the scarcity of orthogonal resources in current wireless communications. On the other hand, integrating the satellite within terrestrial networks as an initiative of 3GPP since its Release 15 entails the need for new forms of multiple access between terrestrial and non-terrestrial users. This paper studies constellation schemes as a new domain to enhance the state-of-the-art multipl…
Large dimensional random matrix theory (RMT) has provided an efficient analytical tool to understand multiple-input multiple-output (MIMO) channels and to aid the design of MIMO wireless communication systems. However, previous studies based on large dimensional RMT rely on the assumption that the transmit correlation matrix is diagonal or the propagation channel matrix is Gaussian. There is an increasing interest in the channels where the transmit correlation matrices are generally nonnegative definite and the channel entries are non-Gaussian. This class of channel models appears in several a…
