arXiv subjects

Min Dong

Publications and source records attributed to Min Dong.

At least 19 recordsLinked to original sources

arXiv2025

Privacy Enhancement in Over-the-Air Federated Learning via Adaptive Receive Scaling

In Federated Learning (FL) with over-the-air aggregation, the quality of the signal received at the server critically depends on the receive scaling factors. While a larger scaling factor can reduce the effective noise power and improve training performance, it also compromises the privacy of devices by reducing uncertainty. In this work, we aim to adaptively design the receive scaling factors across training rounds to balance the trade-off between training convergence and privacy in an FL system under dynamic channel conditions. We formulate a stochastic optimization problem that minimizes the overall R\'enyi differential privacy (RDP) leakage over the entire training process, subject to a long-term constraint that ensures convergence of the global loss function. Our problem depends on unknown future information, and we observe that standard Lyapunov optimization is not applicable. Thus, we develop a new online algorithm, termed AdaScale, based on a sequence of novel per-round problems that can be solved efficiently. We further derive upper bounds on the dynamic regret and constraint violation of AdaSacle, establishing that it achieves diminishing dynamic regret in terms of time-averaged RDP leakage while ensuring convergence of FL training to a stationary point. Numerical experiments on canonical classification tasks show that our approach effectively reduces RDP and DP leakages compared with state-of-the-art benchmarks without compromising learning performance.

cs.IT↗

arXiv2025

Robust Segmented Analog Broadcast Design to Accelerate Wireless Federated Learning

We consider downlink broadcast design for federated learning (FL) in a wireless network with imperfect channel state information (CSI). Aiming to reduce transmission latency, we propose a segmented analog broadcast (SegAB) scheme, where the parameter server, hosted by a multi-antenna base station, partitions the global model parameter vector into segments and transmits multiple parameters from these segments simultaneously over a common downlink channel. We formulate the SegAB transmission and reception processes to characterize FL training convergence, capturing the effects of downlink beamforming and imperfect CSI. To maximize the FL training convergence rate, we establish an upper bound on the expected model optimality gap and show that it can be minimized separately over the training rounds in online optimization, without requiring knowledge of the future channel states. We solve the per-round problem to achieve robust downlink beamforming, by minimizing the worst-case objective via an epigraph representation and a feasibility subproblem that ensures monotone convergence. Simulation with standard classification tasks under typical wireless network setting shows that the proposed SegAB substantially outperforms conventional full-model per-parameter broadcast and other alternatives.

cs.IT↗

arXiv2025

SegOTA: Accelerating Over-the-Air Federated Learning with Segmented Transmission

Federated learning (FL) with over-the-air computation efficiently utilizes the communication resources, but it can still experience significant latency when each device transmits a large number of model parameters to the server. This paper proposes the Segmented Over-The-Air (SegOTA) method for FL, which reduces latency by partitioning devices into groups and letting each group transmit only one segment of the model parameters in each communication round. Considering a multi-antenna server, we model the SegOTA transmission and reception process to establish an upper bound on the expected model learning optimality gap. We minimize this upper bound, by formulating the per-round online optimization of device grouping and joint transmit-receive beamforming, for which we derive efficient closed-form solutions. Simulation results show that our proposed SegOTA substantially outperforms the conventional full-model OTA approach and other common alternatives.

cs.IT↗

arXiv2025

Improving Wireless Federated Learning via Joint Downlink-Uplink Beamforming over Analog Transmission

Federated learning (FL) over wireless networks using analog transmission can efficiently utilize the communication resource but is susceptible to errors caused by noisy wireless links. In this paper, assuming a multi-antenna base station, we jointly design downlink-uplink beamforming to maximize FL training convergence over time-varying wireless channels. We derive the round-trip model updating equation and use it to analyze the FL training convergence to capture the effects of downlink and uplink beamforming and the local model training on the global model update. Aiming to maximize the FL training convergence rate, we propose a low-complexity joint downlink-uplink beamforming (JDUBF) algorithm, which adopts a greedy approach to decompose the multi-round joint optimization and convert it into per-round online joint optimization problems. The per-round problem is further decomposed into three subproblems over a block coordinate descent framework, where we show that each subproblem can be efficiently solved by projected gradient descent with fast closed-form updates. An efficient initialization method that leads to a closed-form initial point is also proposed to accelerate the convergence of JDUBF. Simulation demonstrates that JDUBF substantially outperforms the conventional separate-link beamforming design.

cs.IT↗

arXiv2025

Power-Efficient Over-the-Air Aggregation with Receive Beamforming for Federated Learning

This paper studies power-efficient uplink transmission design for federated learning (FL) that employs over-the-air analog aggregation and multi-antenna beamforming at the server. We jointly optimize device transmit weights and receive beamforming at each FL communication round to minimize the total device transmit power while ensuring convergence in FL training. Through our convergence analysis, we establish sufficient conditions on the aggregation error to guarantee FL training convergence. Utilizing these conditions, we reformulate the power minimization problem into a unique bi-convex structure that contains a transmit beamforming optimization subproblem and a receive beamforming feasibility subproblem. Despite this unconventional structure, we propose a novel alternating optimization approach that guarantees monotonic decrease of the objective value, to allow convergence to a partial optimum. We further consider imperfect channel state information (CSI), which requires accounting for the channel estimation errors in the power minimization problem and FL convergence analysis. We propose a CSI-error-aware joint beamforming algorithm, which can substantially outperform one that does not account for channel estimation errors. Simulation with canonical classification datasets demonstrates that our proposed methods achieve significant power reduction compared to existing benchmarks across a wide range of parameter settings, while attaining the same target accuracy under the same convergence rate.

cs.IT↗

arXiv2025

Constrained Over-the-Air Model Updating for Wireless Online Federated Learning with Delayed Information

We study online federated learning over a wireless network, where the central server updates an online global model sequence to minimize the time-varying loss of multiple local devices over time. The server updates the global model through over-the-air model-difference aggregation from the local devices over a noisy multiple-access fading channel. We consider the practical scenario where information on both the local loss functions and the channel states is delayed, and each local device is under a time-varying power constraint. We propose Constrained Over-the-air Model Updating with Delayed infOrmation (COMUDO), where a new lower-and-upper-bounded virtual queue is introduced to counter the delayed information and control the hard constraint violation. We show that its local model updates can be efficiently computed in closed-form expressions. Furthermore, through a new Lyapunov drift analysis, we show that COMUDO provides bounds on the dynamic regret, static regret, and hard constraint violation. Simulation results on image classification tasks under practical wireless network settings show substantial accuracy gain of COMUDO over state-of-the-art approaches, especially in the low-power region.

cs.DC↗

arXiv2024

Computation-and-Communication Efficient Coordinated Multicast Beamforming in Massive MIMO Networks

The main challenges in designing downlink coordinated multicast beamforming in massive multiple-input multiple output (MIMO) cellular networks are the complex computational solutions and significant fronthaul overhead for centralized coordination. This paper proposes a coordinated multicast beamforming solution that is both computation and communication efficient. For joint BS coordination with individual base station transmit power budgets, we first obtain the optimal structure of coordinated multicast beamforming. It reveals that the beamformer at each BS is naturally distributed and only depends on the local channel state information (CSI) at its serving BS. Moreover, the optimal beamformer is a weighted minimum mean square error (MMSE) beamformer with a low-dimensional structure of unknown weights to be optimized, independent of the number of BS antennas. Utilizing the optimal structural properties, we propose fast algorithms to determine the unknown parameters for the optimal beamformer. The main iterative algorithm decomposes the problem into small subproblems, yielding only closed/semi-closed form updates. Furthermore, we propose a semi-distributed computing approach for the proposed algorithm that allows each BS to compute its beamformer based on the local CSI without the need for global CSI sharing, resulting in the fronthaul overhead independent of the number of BS antennas. We further extend our results to the design under the imperfect CSI and other coordination scenarios. Simulation results demonstrate that our proposed methods can achieve near-optimal performance with significantly lower computational time for massive MIMO systems than the conventional approaches.

eess.SP↗

arXiv2024

Uplink Over-the-Air Aggregation for Multi-Model Wireless Federated Learning

We propose an uplink over-the-air aggregation (OAA) method for wireless federated learning (FL) that simultaneously trains multiple models. To maximize the multi-model training convergence rate, we derive an upper bound on the optimality gap of the global model update, and then, formulate an uplink joint transmit-receive beamforming optimization problem to minimize this upper bound. We solve this problem using the block coordinate descent approach, which admits low-complexity closed-form updates. Simulation results show that our proposed multi-model FL with fast OAA substantially outperforms sequentially training multiple models under the conventional single-model approach.

cs.IT↗

arXiv2024

Fast Group Scheduling for Downlink Large-Scale Multi-Group Multicast Beamforming

Next-generation wireless networks need to handle massive user access effectively. This paper addresses the problem of joint group scheduling and multicast beamforming for downlink transmission with many active user groups. Aiming to maximize the minimum user throughput, we propose a three-phase approach to tackle this difficult joint optimization problem efficiently. In Phase 1, we utilize the optimal multicast beamforming structure obtained recently to find the group-channel directions for all groups. We propose two low-complexity group scheduling algorithms in Phase 2, which determine the subset of groups in each time slot sequentially and the total number of time slots required for all groups. The first algorithm measures the level of spatial separation among groups and selects the dissimilar groups that maximize the minimum user rate into the same time slot. In contrast, the second algorithm first identifies the spatially correlated groups via a learning-based clustering method based on the group-channel directions, and then separates spatially similar groups into different time slots. Finally, the multicast beamformers for the scheduled groups are obtained in each time slot by a computationally efficient method. Simulation results show that our proposed scheduling methods can effectively capture the level of spatial separation among groups to improve the minimum user throughput over the conventional approach that serves all groups in a single time slot or one group per time slot, and can be executed with low computational complexity.

cs.IT↗

arXiv2023

Fast and Scalable Beamforming for RIS-Assisted Downlink Multi-group Multicasting

This paper considers downlink multi-group multicasting via beamforming facilitated by a reconfigurable intelligent surface (RIS). We develop a fast and scalable algorithm for the joint base station (BS) and RIS beamforming optimization to minimize the transmit power while meeting user quality-of-service (QoS) targets. By analyzing the structure of the QoS constraints, we reformulate the problem and show that the joint beamforming optimization inherently consists of a multicast beamforming QoS problem for the BS and a passive multicast beamforming max-min-fair (MMF) problem for the RIS. We propose a fast alternating multicast beamforming (AMBF) algorithm to effectively solve the two subproblems alternatingly. For the BS multicast subproblem, we utilize the optimal multicast beamforming structure to efficiently determine the BS beamformers. For the RIS multicast subproblem, we reformulate the MMF problem and apply a first-order projected subgradient algorithm (PSA), which yields simple closed-form updates. The computational complexity of the AMBF algorithm grows linearly with the number of RIS elements and BS antennas. We further consider joint BS and RIS beamforming for the weighted MMF design objective, subject to the BS transmit power budget. We propose an alternating PSA (APSA) fast algorithm to compute the beamforming solutions for the BS and RIS. APSA consists of only closed-form updates per iteration, yielding linear computational complexity in the number of RIS elements and BS antennas. Simulation results show the efficacy of our proposed algorithms in terms of performance and computational cost compared to alternative methods.

eess.SP↗

arXiv2023

Multi-Model Wireless Federated Learning with Downlink Beamforming

This paper studies the design of wireless federated learning (FL) for simultaneously training multiple machine learning models. We consider round robin device-model assignment and downlink beamforming for concurrent multiple model updates. After formulating the joint downlink-uplink transmission process, we derive the per-model global update expression over communication rounds, capturing the effect of beamforming and noisy reception. To maximize the multi-model training convergence rate, we derive an upper bound on the optimality gap of the global model update and use it to formulate a multi-group multicast beamforming problem. We show that this problem can be converted to minimizing the sum of inverse received signal-to-interference-plus-noise ratios, which can be solved efficiently by projected gradient descent. Simulation shows that our proposed multi-model FL solution outperforms other alternatives, including conventional single-model sequential training and multi-model zero-forcing beamforming.

cs.IT↗

arXiv2023

Design and Optimization of Heterogeneous Coded Distributed Computing with Nonuniform File Popularity

This paper studies MapReduce-based heterogeneous coded distributed computing (CDC) where, besides different computing capabilities at workers, input files to be accessed by computing jobs have nonuniform popularity. We propose a file placement strategy that can handle an arbitrary number of input files. Furthermore, we design a nested coded shuffling strategy that can efficiently manage the nonuniformity of file popularity to maximize the coded multicasting opportunity. We then formulate the joint optimization of the proposed file placement and nested shuffling design variables to optimize the proposed CDC scheme. To reduce the high computational complexity in solving the resulting mixed-integer linear programming (MILP) problem, we propose a simple two-file-group-based file placement approach to obtain an approximate solution. Numerical results show that the optimized CDC scheme outperforms other alternatives. Also, the proposed two-file-group-based approach achieves nearly the same performance as the conventional branch-and-cut method in solving the MILP problem but with substantially lower computational complexity that is scalable over the number of files and workers. For computing jobs with aggregate target functions that commonly appear in machine learning applications, we propose a heterogeneous compressed CDC (C-CDC) scheme to further improve the shuffling efficiency. The C-CDC scheme uses a local data aggregation technique to compress the data to be shuffled for the shuffling load reduction. We again optimize the proposed C-CDC scheme and explore the two-file-group-based low-complexity approach for an approximate solution. Numerical results show the proposed C-CDC scheme provides a considerable shuffling load reduction over the CDC scheme, and also, the two-file-group-based file placement approach maintains good performance.

cs.IT↗

arXiv2023

Joint Downlink-Uplink Beamforming for Wireless Multi-Antenna Federated Learning

We study joint downlink-uplink beamforming design for wireless federated learning (FL) with a multi-antenna base station. Considering analog transmission over noisy channels and uplink over-the-air aggregation, we derive the global model update expression over communication rounds. We then obtain an upper bound on the expected global loss function, capturing the downlink and uplink beamforming and receiver noise effect. We propose a low-complexity joint beamforming algorithm to minimize this upper bound, which employs alternating optimization to breakdown the problem into three subproblems, each solved via closed-form gradient updates. Simulation under practical wireless system setup shows that our proposed joint beamforming design solution substantially outperforms the conventional separate-link design approach and nearly attains the performance of ideal FL with error-free communication links.

cs.IT↗

arXiv2023

Decentralized Caching under Nonuniform File Popularity and Size: Memory-Rate Tradeoff Characterization

This paper aims to characterize the memory-rate tradeoff for decentralized caching under nonuniform file popularity and size. We consider a recently proposed decentralized modified coded caching scheme (D-MCCS) and formulate the cache placement optimization problem to minimize the average rate for the D-MCCS. To solve this challenging non-convex optimization problem, we first propose a successive Geometric Programming (GP) approximation algorithm, which guarantees convergence to a stationary point but has high computational complexity. Next, we develop a low-complexity file-group-based approach, where we propose a popularity-first and size-aware (PF-SA) cache placement strategy to partition files into two groups, taking into account the nonuniformity in file popularity and size. Both algorithms do not require the knowledge of active users beforehand for cache placement. Numerical results show that they perform very closely to each other. We further develop a lower bound for decentralized caching under nonuniform file popularity and size as a non-convex optimization problem and solved it using a similar successive GP approximation algorithm. We show that the D-MCCS with the optimized cache placement attains this lower bound when no more than two active users request files at a time. The same is true for files with uniform size but nonuniform popularity and the optimal cache placement being symmetric among files. In these cases, the optimized DMCCS characterizes the exact memory-rate tradeoff for decentralized caching. For general cases, our numerical results show that the average rate achieved by the optimized D-MCCS is very close to the lower bound.

cs.IT↗

arXiv2023

Beamforming and Device Selection Design in Federated Learning with Over-the-air Aggregation

Federated learning (FL) with over-the-air computation can efficiently utilize the communication bandwidth but is susceptible to analog aggregation error. Excluding those devices with weak channel conditions can reduce the aggregation error, but it also limits the amount of local training data for FL, which can reduce the training convergence rate. In this work, we jointly design uplink receiver beamforming and device selection for over-the-air FL over time-varying wireless channels to maximize the training convergence rate. We reformulate this stochastic optimization problem into a mixed-integer program using an upper bound on the global training loss over communication rounds. We then propose a Greedy Spatial Device Selection (GSDS) approach, which uses a sequential procedure to select devices based on a measure capturing both the channel strength and the channel correlation to the selected devices. We show that given the selected devices, the receiver beamforming optimization problem is equivalent to downlink single-group multicast beamforming. To reduce the computational complexity, we also propose an Alternating-optimization-based Device Selection and Beamforming (ADSBF) approach, which solves the receiver beamforming and device selection subproblems alternatingly. In particular, despite the device selection being an integer problem, we are able to develop an efficient algorithm to find its optimal solution. Simulation results with real-world image classification demonstrate that our proposed methods achieve faster convergence with significantly lower computational complexity than existing alternatives. Furthermore, although ADSBF shows marginally inferior performance to GSDS, it offers the advantage of lower computational complexity when the number of devices is large.

cs.IT↗

arXiv2022

Ultra-Low-Complexity Algorithms with Structurally Optimal Multi-Group Multicast Beamforming in Large-Scale Systems

In this work, we propose ultra-low-complexity design solutions for multi-group multicast beamforming in large-scale systems. For the quality-of-service (QoS) problem, by utilizing the optimal multicast beamforming structure obtained recently in [2], we convert the original problem into a non-convex weight optimization problem of a lower dimension and propose two fast first-order algorithms to solve it. Both algorithms are based on successive convex approximation (SCA) and provide fast iterative updates to solve each SCA subproblem. The first algorithm uses a saddle point reformulation in the dual domain and applies the extragradient method with an adaptive step-size procedure to find the saddle point with simple closed-form updates. The second algorithm adopts the alternating direction method of multipliers (ADMM) method by converting each SCA subproblem into a favorable ADMM structure. The structure leads to simple closed-form ADMM updates, where the problem in each update block can be further decomposed into parallel subproblems of small sizes, for which closed-form solutions are obtained. We also propose efficient initialization methods to obtain favorable initial points that facilitate fast convergence. Furthermore, taking advantage of the proposed fast algorithms, for the max-min fair (MMF) problem, we propose a simple closed-form scaling scheme that directly uses the solution obtained from the QoS problem, avoiding the conventional computationally expensive method that iteratively solves the inverse QoS problem. We further develop lower and upper bounds on the performance of this scaling scheme. Simulation results show that the proposed algorithms offer near-optimal performance with substantially lower computational complexity than the state-of-the-art algorithms for large-scale systems.

cs.IT↗

arXiv2022

Online Distributed Coordinated Precoding for Virtualized MIMO Networks with Delayed CSI

We consider online wireless network virtualization (WNV) in a multi-cell multiple-input multiple output (MIMO) system with delayed feedback of channel state information (CSI). Multiple service providers (SPs) simultaneously share the base station resources of an infrastructure provider (InP). We aim at minimizing the accumulated precoding deviation of the InP's actual precoder from the SPs' virtualization demands via managing both inter-SP and inter-cell interference, subject to both long-term and short-term per-cell transmit power constraints. We develop an online coordinated precoding solution and show that it provides provable performance bounds. Our precoding solution is fully distributed at each cell, based only on delayed local CSI. Furthermore, it has a closed-form expression with low computational complexity. Finally, simulation results demonstrate the substantial performance gain of our precoding solution over the current best alternative.

cs.IT↗

arXiv2021

Fast First-Order Algorithm for Large-Scale Max-Min Fair Multi-Group Multicast Beamforming

We propose a first-order fast algorithm for the weighted max-min fair (MMF) multi-group multicast beamforming problem in large-scale systems. Utilizing the optimal multicast beamforming structure obtained recently, we convert the nonconvex MMF problem into a min-max weight minimization problem and show that it is a weakly convex problem. We propose using the projected subgradient algorithm (PSA) to solve the problem directly, instead of the conventional method that requires iteratively solving its inverse problem. We show that PSA for our problem has closed-form updates and thus is computationally cheap. Furthermore, PSA converges to a near-stationary point of our problem within finite time. Simulation results show that our PSA-based algorithm offers near-optimal performance with considerably lower computational complexity than existing methods for large-scale systems.

cs.IT↗