publications

This paper investigates the optimization of transmitting the encoder outputs, termed semantic features (SFs), in semantic communication (SC). We begin by modeling the entire communication process from the encoder output to the decoder input, encompassing the physical channel and all transceiver operations, as the SF channel, thereby establishing an encoder-SF channel-decoder pipeline. In contrast to prior studies that assume a fixed SF channel, we note that the SF channel is configurable, as its characteristics are shaped by various transmission and reception strategies, such as power allocation. Based on this observation, we formulate the SF channel optimization problem under a mutual information constraint between the SFs and their reconstructions, and analytically derive the optimal SF channel under a linear encoder-decoder structure and Gaussian source assumption. Building on this analysis, we propose a joint optimization framework for the encoder-decoder and SF channel applicable to both analog and digital SC systems. To realize the optimized SF channel, we also propose a physical-layer calibration strategy that enables real-time power control and adaptation to varying channel conditions. Simulation results demonstrate that the proposed SF channel optimization achieves superior task performance under various communication environments.

This paper investigates unequal error protection (UEP) in digital semantic communication, where semantically important bits require substantially higher reliability than less critical ones. To characterize this heterogeneity, we introduce a novel perspective that treats learned bit-flip probabilities of semantic bits as target error protection levels, thereby directly linking semantic importance to bit-level reliability. This formulation reveals that the required protection levels of the semantic bits may differ by several orders of magnitude, making short-block coding more advantageous than conventional long-block designs. Motivated by this, we develop two UEP frameworks that minimize total blocklength under heterogeneous reliability constraints. First, we propose a bit-level UEP framework based on repetition coding, providing an analytically tractable solution that precisely meets per-bit protection requirements. Second, to improve energy and blocklength efficiency, we design a block-level UEP framework in which the semantic bits are partitioned into short blocks with similar protection levels. Guided by finite blocklength capacity analysis, we derive a closed-form threshold condition for beneficial partitioning and develop a systematic algorithm for integrating modern channel codes. Simulation results on image transmission tasks demonstrate substantial gains in both task performance and transmission efficiency compared with conventional equal-protection schemes.

This paper proposes a novel framework for rate-adaptive semantic communication based on multi-stage vector quantization (VQ), termed MSVQ-SC. Unlike conventional single-stage VQ approaches, which require exponentially larger codebooks to achieve higher fidelity, the proposed framework decomposes the quantization process into multiple stages and dynamically activates both stages and individual VQ modules. This design enables fine-grained rate adaptation under varying bit constraints while mitigating computational complexity and the codebook collapse problem. To optimize performance, we formulate a module selection problem that minimizes task loss subject to a rate constraint and solve it using an incremental allocation algorithm. Furthermore, we extend the framework by incorporating entropy coding to exploit non-uniform codeword distributions, further reducing communication overhead. Simulation results on the CIFAR-10 dataset demonstrate that the proposed framework outperforms existing digital semantic communication methods, achieving superior semantic fidelity with lower complexity while providing flexible and fine-grained rate control.

This paper presents a robust beam alignment technique for millimeter-wave communications in low signal-to-noise ratio (SNR) environments. The core strategy of our technique is to repeatedly transmit the most probable beam candidates to reduce beam misalignment probability induced by noise. Specifically, for a given beam training overhead, both the selection of candidates and the number of repetitions for each beam candidate are optimized based on channel prior information. To achieve this, a deep neural network is employed to learn the prior probability of the optimal beam at each location. The beam misalignment probability is then analyzed based on the channel prior, forming the basis for an optimization problem aimed at minimizing the analyzed beam misalignment probability. A closed-form solution is derived for a special case with two beam candidates, and an efficient algorithm is developed for general cases with multiple beam candidates. Simulation results using the DeepMIMO dataset demonstrate the superior performance of our technique in dynamic low-SNR communication environments when compared to existing beam alignment techniques.

This paper presents a novel importance-aware quantization, subcarrier mapping, and power allocation (IA-QSMPA) framework for semantic communication in multiple-input multiple-output orthogonal frequency division multiplexing (MIMO-OFDM) systems, empowered by a pretrained Vision Transformer (ViT). The proposed framework exploits attention-based importance extracted from a pretrained ViT to jointly optimize quantization levels, subcarrier mapping, and power allocation. Specifically, IA-QSMPA maps semantically important features to high-quality subchannels and allocates resources in accordance with their contribution to task performance and communication latency. To efficiently solve the resulting nonconvex optimization problem, a block coordinate descent algorithm is employed. The framework is further extended to operate under finite blocklength transmission, where communication errors may occur. In this setting, a segment-wise linear approximation of the channel dispersion penalty is introduced to enable efficient joint optimization under practical constraints. Simulation results on multi-view image classification and single-object detection tasks demonstrate that IA-QSMPA significantly outperforms conventional methods in both ideal and finite blocklength transmission scenarios, achieving superior task performance and communication efficiency.

This paper proposes a novel end-to-end digital semantic communication framework based on multi-codebook vector quantization (VQ), referred to as ESC-MVQ. Unlike prior approaches that rely on end-to-end training with a specific power or modulation scheme, often under a particular channel condition, ESC-MVQ models a channel transfer function as parallel binary symmetric channels (BSCs) with trainable bit-flip probabilities. Building on this model, ESC-MVQ jointly trains multiple VQ codebooks and their associated bit-flip probabilities with a single encoder-decoder pair. To maximize inference performance when deploying ESC-MVQ in digital communication systems, we devise an optimal communication strategy that jointly optimizes codebook assignment, adaptive modulation, and power allocation. To this end, we develop an iterative algorithm that selects the most suitable VQ codebook for semantic features and flexibly allocates power and modulation schemes across the transmitted symbols. Simulation results demonstrate that ESC-MVQ, using a single encoder-decoder pair, outperforms existing digital semantic communication methods in both performance and memory efficiency, offering a scalable and adaptive solution for realizing digital semantic communication in diverse channel conditions.

Semantic encoders and decoders for digital semantic communication (SC) often struggle to adapt to variations in unpredictable channel environments and diverse system designs. To address these challenges, this paper proposes a novel framework for training semantic encoders and decoders to enable channel-adaptive digital SC. The core idea is to use binary symmetric channel (BSC) as a universal representation of generic digital communications, eliminating the need to specify channel environments or system designs. Based on this idea, our framework employs parallel BSCs to equivalently model the relationship between the encoder’s output and the decoder’s input. The bit-flip probabilities of these BSCs are treated as trainable parameters during end-to-end training, with varying levels of regularization applied to address diverse requirements in practical systems. The advantage of our framework is justified by developing a training-aware communication strategy for the inference stage. This strategy makes communication bit errors align with the pre-trained bit-flip probabilities by adaptively selecting power and modulation levels based on practical requirements and channel conditions. Simulation results demonstrate that the proposed framework outperforms existing training approaches in terms of both task performance and power consumption.

This letter presents a deep learning (DL)-based modulation and power control (MPC) framework for two bit error rate (BER)-based optimization problems under parallel fading channels. First, we aim to minimize BER by designing two neural networks, ModNet and PowerNet, which optimize modulation and power levels, respectively, while satisfying their constraints. Second, we seek to minimize total power while ensuring a target BER by training ModNet for modulation level decision, followed by a convex optimization process for power allocation. Simulation results validate the effectiveness of the proposed DL-based MPC framework, demonstrating lower BER, reduced total power consumption, and faster simulation time compared to existing MPC baselines.

This paper presents a semantic communication framework for orthogonal frequency division multiplexing (OFDM) systems. In this framework, we first introduce an end-to-end training strategy which leverages binary symmetric channels (BSCs) to model OFDM communication errors, thereby eliminating the need to specify channel distributions, modulation order, and transmission power during end-to-end training. We then propose a joint modulation order and power optimization scheme for OFDM systems designed for our end-to-end training strategy. Our optimization aims to maximize the transmission rate while satisfying target bit-error rate and power constraints. Through simulations, we demonstrate the superiority of our framework compared to existing schemes.

Semantic communications provide significant performance gains over traditional communications by transmitting task-relevant semantic features through wireless channels. However, most existing studies rely on end-to-end (E2E) training of neural-type encoders and decoders to ensure effective transmission of these semantic features. To enable semantic communications without relying on E2E training, this article presents a vision transformer (ViT)-based semantic communication system with importance-aware quantization (IAQ) for wireless image transmission. The core idea of the presented system is to leverage the attention scores of a pretrained ViT model to quantify the importance levels of image patches. Based on this idea, our IAQ framework assigns different quantization bits to image patches based on their importance levels. This is achieved by formulating a weighted quantization error minimization problem, where the weight is set to be an increasing function of the attention score. Then, an optimal incremental allocation method and a low-complexity water-filling method are devised to solve the formulated problem. Our framework is further extended for realistic digital communication systems by modifying the bit allocation problem and the corresponding allocation methods based on an equivalent binary symmetric channel (BSC) model. Simulations on single-view image classification, multiview image classification, and single-object detection tasks demonstrate that our IAQ framework outperforms conventional image compression methods under both error-free and realistic communication scenarios.

In this article, we present a novel approach for joint activity detection (AD), channel estimation (CE), and data detection (DD) in uplink grant-free nonorthogonal multiple access (NOMA) systems. Our approach employs an iterative and parallel interference removal strategy inspired by parallel interference cancellation (PIC), enhanced with deep learning to jointly tackle the AD, CE, and DD problems. Based on this approach, we develop three PIC frameworks, each of which is designed for either coherent or noncoherence schemes. The first framework performs joint AD and CE using received pilot signals in the coherent scheme. Building upon this framework, the second framework utilizes both the received pilot and data signals for CE, further enhancing the performances of AD, CE, and DD in the coherent scheme. The third framework is designed to accommodate the noncoherent scheme involving a small number of data bits, which simultaneously performs AD and DD. Through joint loss functions and interference cancellation modules, our approach supports end-to-end training, contributing to enhanced performances of AD, CE, and DD for both coherent and noncoherent schemes. Simulation results demonstrate the superiority of our approach over traditional techniques, exhibiting enhanced performances of AD, CE, and DD while maintaining lower computational complexity.

This article proposes a novel communication-efficient split learning (SL) framework, named SplitFC, which reduces the communication overhead required for transmitting intermediate features and gradient vectors during the SL training process. The key idea of SplitFC is to leverage different dispersion degrees exhibited in the columns of the matrices. SplitFC incorporates two compression strategies: 1) adaptive feature-wise dropout and 2) adaptive feature-wise quantization. In the first strategy, the intermediate feature vectors are dropped with adaptive dropout probabilities determined based on the standard deviation of these vectors. Then, by the chain rule, the intermediate gradient vectors associated with the dropped feature vectors are also dropped. In the second strategy, the non-dropped intermediate feature and gradient vectors are quantized using adaptive quantization levels determined based on the ranges of the vectors. To minimize the quantization error, the optimal quantization levels of this strategy are derived in a closed-form expression. Simulation results on the MNIST, CIFAR-100, and CelebA datasets demonstrate that SplitFC outperforms state-of-the-art SL frameworks by significantly reducing communication overheads while maintaining high accuracy.

In this paper, we propose a novel joint source-channel coding (JSCC) approach for channel-adaptive digital semantic communications. In semantic communication systems with digital modulation and demodulation, robust design of JSCC encoder and decoder becomes challenging not only due to the unpredictable dynamics of channel conditions but also due to diverse modulation orders. To address this challenge, we first develop a new demodulation method which assesses the uncertainty of the demodulation output to improve the robustness of the digital semantic communication system. We then devise a robust training strategy which enhances the robustness and flexibility of the JSCC encoder and decoder against diverse channel conditions and modulation orders. To this end, we model the relationship between the encoder’s output and decoder’s input using binary symmetric erasure channels and then sample the parameters of these channels from diverse distributions. We also develop a channel-adaptive modulation technique for an inference phase, in order to reduce the communication latency while maintaining task performance. In this technique, we adaptively determine modulation orders for the latent variables based on channel conditions. Using simulations, we demonstrate the superior performance of the proposed JSCC approach for image classification, reconstruction, and retrieval tasks compared to existing JSCC approaches.

In this paper, we propose a communication-efficient federated learning (FL) framework to enhance the convergence rate of FL under limited uplink capacity. The core idea of our framework is to transmit the values and positions of the top-S entries of a local model update, determined in terms of magnitude. When transmitting the top-S values, we first apply a linear transformation that enforces the transformed values to behave like Gaussian random variables. We then employ a scalar quantizer optimized for Gaussian distributions, leading to minimizing compression errors. When reconstructing the top-S values, we develop a linear minimum mean squared error method based on the Bussgang decomposition. Additionally, we introduce an error feedback strategy to compensate for both compression and reconstruction errors. We analyze the convergence rate of our framework under general considerations, including a non-convex loss function. Based on our analytical results, we optimize the key parameters of our framework to maximize the convergence rate for a given uplink capacity. Simulation results demonstrate that our framework achieves more than a 2.2%, 1.1%, and 1.4% increase in classification accuracy for the MNIST, CIFAR-10, and CIFAR-100 datasets, respectively, compared to state-of-the-art FL frameworks under limited uplink capacity.

This paper presents a novel split learning (SL) framework, referred to as SplitMAC, which reduces the latency of SL by leveraging simultaneous uplink transmission over multiple access channels. The key strategy is to divide devices into multiple groups and allow the devices within the same group to simultaneously transmit their smashed data and device-side models over the multiple access channels. The optimization problem of device grouping to minimize SL latency is formulated, and the benefit of device grouping in reducing the uplink latency of SL is theoretically derived. By examining a two-device grouping case, two asymptotically-optimal algorithms are devised for device grouping in low and high signal-to-noise ratio (SNR) scenarios, respectively. By merging these algorithms, a near-optimal device grouping algorithm is proposed to cover a wide range of SNR. Although our theoretical analysis holds only for the two-device case, our SL framework is also extended to consider practical fading channels and to support a general group size. Simulation results demonstrate that our SL framework with the proposed device grouping algorithm is superior to existing SL frameworks in reducing SL latency.

In this paper, a new communication-efficient federated learning (FL) framework is proposed, inspired by vector quantized compressed sensing. The basic strategy of the proposed framework is to compress the local model update at each device by applying dimensionality reduction followed by vector quantization. Subsequently, the global model update is reconstructed at a parameter server by applying a sparse signal recovery algorithm to the aggregation of the compressed local model updates. By harnessing the benefits of both dimensionality reduction and vector quantization, the proposed framework effectively reduces the communication overhead of local update transmissions. Both the design of the vector quantizer and the key parameters for the compression are optimized so as to minimize the reconstruction error of the global model update under the constraint of wireless link capacity. By considering the reconstruction error, the convergence rate of the proposed framework is also analyzed for a non-convex loss function. Simulation results on the MNIST and FEMNIST datasets demonstrate that the proposed framework can improve classification accuracy by more than 2.4% compared to state-of-the-art FL frameworks when the communication overhead of the local model update transmission is 0.1 bit per local model entry.

In this paper, we present a communication-efficient federated learning framework inspired by quantized compressed sensing. The presented framework consists of gradient compression for wireless devices and gradient reconstruction for a parameter server (PS). Our strategy for gradient compression is to sequentially perform block sparsification, dimensional reduction, and quantization. By leveraging both dimension reduction and quantization, our strategy can achieve a higher compression ratio than one-bit gradient compression. For accurate aggregation of local gradients from the compressed signals, we put forth an approximate minimum mean square error (MMSE) approach for gradient reconstruction using the expectation-maximization generalized-approximate-message-passing (EM-GAMP) algorithm. Assuming Bernoulli Gaussian-mixture prior, this algorithm iteratively updates the posterior mean and variance of local gradients from the compressed signals. We also present a low-complexity approach for the gradient reconstruction. In this approach, we use the Bussgang theorem to aggregate local gradients from the compressed signals, then compute an approximate MMSE estimate of the aggregated gradient using the EM-GAMP algorithm. We also provide a convergence rate analysis of the presented framework. Using the MNIST dataset, we demonstrate that the presented framework achieves almost identical performance with the case that performs no compression, while significantly reducing communication overhead for federated learning.

To enable accurate and reliable indoor localization in a multi-building environment, a novel constrained convolutional neural network (CNN)-based indoor localization system (C-CNNLoc) is proposed using WiFi fingerprinting approach. The proposed network has a sequential structure that firstly classifies a building, followed by estimating the user’s location coordinate within the pre-detected building. Furthermore, the location accuracy is improved by introducing a new loss function that incorporates a penalty term associated with the building boundary. Experimental results illustrate that the proposed method outperforms the existing solutions on the average distance error. The gain comes from that the approach tailored to a multi-building indoor localization with the sequential structure is prone to successfully correct outliers, that is, predicted location coordinates that lie outside the buildings.

Abstract is not yet provided.

Federated fine-tuning of foundation models is impeded by the need to communicate billions of parameters. Low-rank adaptation (LoRA) alleviates this by updating only compact adapter matrices. However, varying client device capabilities lead to different adapter ranks, causing rank heterogeneity that undermines aggregation, and existing reconciliation methods still incur bias or inefficiency. To address this challenge, we propose RB-LoRA, a principled rank-balanced aggregation framework that decomposes each update into rank-wise components and aligns them using analytically derived weights. Experiments on both language and vision models demonstrate consistent improvements under one and three rounds of communication in federated learning.

Abstract is not yet provided.

Semantic communications provide significant performance gains over traditional communications by transmitting task-relevant semantic features through wireless channels. However, most existing studies rely on end-to-end (E2E) training of neural-type encoders and decoders to ensure effective transmission of these semantic features. To enable semantic communications without relying on E2E training, this paper presents a vision transformer (ViT)-based semantic communication system with importance-aware quantization (IAQ) for wireless image transmission. The core idea of the presented system is to leverage the attention scores of a pretrained ViT model to quantify the importance levels of image patches. Then, our IAQ framework assigns different quantization bits to image patches based on their importance levels. This is achieved by formulating a weighted quantization error minimization problem, where the weight is set to be an increasing function of the attention score. Then, an optimal incremental bit-allocation method and a low-complexity water-filling method are devised to solve the formulated problem. Simulations on multi-view image classification tasks show that our IAQ framework outperforms existing quantization methods.

In this paper, we introduce a novel deep learning-assisted parallel interference cancellation (PIC) framework for joint activity detection (AD) and channel estimation (CE) in up-link grant-free non-orthogonal multiple access (NOMA) systems. Our framework employs an iterative and parallel interference removal strategy inspired by PIC, enhanced with deep learning to jointly tackle the AD and CE problems. The proposed framework consists of multiple uniform stages, each containing trainable CE modules and non-parameterized IC modules. Additionally, it integrates AD modules that estimate each device activity in a parallel manner by leveraging the received signals after interference removal processes. Through joint loss functions and IC modules, the proposed framework supports end-to-end training, contributing to enhanced performances of AD and CE. Simulation results demonstrate the superiority of the proposed framework over traditional techniques, exhibiting enhanced performances of AD and CE while maintaining lower computational complexity.

This paper proposes a novel joint source-channel coding (JSCC) approach for robust digital semantic communications. When employing a binary-output JSCC encoder with digital modulation, end-to-end training becomes challenging due to the unpredictable dynamics of channel conditions. To address this challenge, we first develop a new demodulation method which assesses the uncertainty of the demodulation output to improve the robustness of the digital semantic communication system. We then devise a robust training strategy which enhances the robustness and flexibility of the JSCC encoder and decoder against diverse channel conditions. To this end, we model the relationship between the encoder’s output and decoder’s input using binary symmetric erasure channels and then sample the parameters of these channels from diverse distributions. Using simulations, we demonstrate the superior performance of the proposed JSCC approach for image classification and reconstruction tasks compared to existing JSCC approaches.

This paper presents a robust beam alignment technique for millimeter-wave communications in low signal-to-noise ratio (SNR) regimes. The basic strategy of this technique involves the repeated transmission of beam candidates, aimed at minimizing the beam misalignment probability induced by noise. In this strategy, however, the beam training overhead becomes impractically significant when both the numbers of beam candidates and beam repetitions are large. To address this challenge, the presented technique aims at optimizing both the selection of beam candidates and the number of repetitions for each candidate based on channel prior information. In the presented technique, a deep neural network is employed to learn the prior probability of the optimal beam at each location. The beam misalignment probability is then analyzed based on the channel prior, and a practical algorithm is developed to find the optimal beam repetition strategy to minimize the beam misalignment probability. Simulation results using the DeepMIMO dataset demonstrate the superior performance of the presented technique in dynamic low-SNR communication environments compared to existing beam alignment techniques.

In this paper, a communication-efficient federated learning (FL) framework is proposed, which leverages ideas from vector quantized compressed sensing, for the first time, to compress the local model updates at wireless devices in FL. For the compression, each local model update is projected onto a lower dimensional space; then, the projected local model update is quantized by using a vector quantizer. The global model update at a parameter server is reconstructed by using a sparse signal recovery algorithm on the aggregation of the compressed local model updates. A key feature of our compression strategy is that the local model update after the projection is effectively modeled as a Gaussian random vector by the central limit theorem. Inspired by this feature, the optimal vector quantizer is derived for minimizing the compression error of the local model update. Simulation results on the MNIST dataset demonstrate that the proposed framework that uses 0.5 bit to represent each local model update entry shows less than a 1% decrease in classification accuracy compared to FL without local update compression.

Federated learning (FL) is a decentralized artificial intelligence technique for training a global model on a parameter server (PS) through collaboration with wireless devices, each with its own local training data set. In this paper, we present a communication-efficient FL framework which consists of gradient compression and reconstruction strategies based on quantized compressed sensing (QCS). The key idea of the gradient compression strategy is to compress-and-quantize a local gradient vector computed at each device after sparsifying this vector in a block wise fashion. Our gradient compression strategy can make communication overhead less than one bit per gradient entry. For accurate reconstruction of the local gradient from the compressed signals at the PS, we employ a expectation-maximization generalized-approximate-message-passing algorithm. The algorithm iteratively computes an approximate minimum mean square error solution of the local gradient, while learning the unknown model parameters of the Bernoulli Gaussian-mixture prior. Using the MNIST data set, we demonstrate that the presented FL framework can achieve almost identical classification performance with the case that performs no compression, while achieving a significant reduction of communication overhead.

In the recent 5G era, according to the rapid development of Internet-of-Things technologies along with smart devices and expansion of its application, the indoor localization techniques using wireless signals have been extensively studied. It is a very challenging task to develop an indoor localization technique with high location accuracy and low complexity in various indoor environments. Among many indoor localization techniques, fingerprint technique using Wi-Fi signals has been received the greatest interest from academia and industry because location estimation is possible without the need for installing separate equipment and constructing infrastructure. Recently, the accuracy of indoor localization has been largely improved as machine learning and deep learning technologies, which have been rapidly developed, have been incorporated into Wi-Fi fingerprints. Therefore, in this paper, we introduce the state-of-the-art trends and pros-and-cons of indoor localization techniques based on Wi-Fi fingerprint utilizing machine learning and deep learning technologies. Furthermore, we discuss new research directions and issues based on the described trends of indoor localization techniques for Wi-Fi fingerprint.