Searcharxiv⌕ Search

arXiv subjects

Yik-Chung Wu

Publications and source records attributed to Yik-Chung Wu.

At least 55 records · Page 3Linked to original sources

A General Optimization Framework for Tackling Distance Constraints in Movable Antenna-Aided Systems

The recently emerged movable antenna (MA) shows great promise in leveraging spatial degrees of freedom to enhance the performance of wireless systems. However, resource allocation in MA-aided systems faces challenges due to the nonconvex and coupled constraints on antenna positions. This paper systematically reveals the challenges posed by the minimum antenna separation distance constraints. Furthermore, we propose a penalty optimization framework for resource allocation under such new constraints for MA-aided systems. Specifically, the proposed framework separates the non-convex and coupled antenna distance constraints from the movable region constraints by introducing auxiliary variables. Subsequently, the resulting problem is efficiently solved by alternating optimization, where the optimization of the original variables resembles that in conventional resource allocation problem while the optimization with respect to the auxiliary variables is achieved in closedform solutions. To illustrate the effectiveness of the proposed framework, we present three case studies: capacity maximization, latency minimization, and regularized zero-forcing precoding. Simulation results demonstrate that the proposed optimization framework consistently outperforms state-of-the-art schemes.

eess.SP↗

pFedLVM: A Large Vision Model (LVM)-Driven and Latent Feature-Based Personalized Federated Learning Framework in Autonomous Driving

Deep learning-based Autonomous Driving (AD) models often exhibit poor generalization due to data heterogeneity in an ever domain-shifting environment. While Federated Learning (FL) could improve the generalization of an AD model (known as FedAD system), conventional models often struggle with under-fitting as the amount of accumulated training data progressively increases. To address this issue, instead of conventional small models, employing Large Vision Models (LVMs) in FedAD is a viable option for better learning of representations from a vast volume of data. However, implementing LVMs in FedAD introduces three challenges: (I) the extremely high communication overheads associated with transmitting LVMs between participating vehicles and a central server; (II) lack of computing resource to deploy LVMs on each vehicle; (III) the performance drop due to LVM focusing on shared features but overlooking local vehicle characteristics. To overcome these challenges, we propose pFedLVM, a LVM-Driven, Latent Feature-Based Personalized Federated Learning framework. In this approach, the LVM is deployed only on central server, which effectively alleviates the computational burden on individual vehicles. Furthermore, the exchange between central server and vehicles are the learned features rather than the LVM parameters, which significantly reduces communication overhead. In addition, we utilize both shared features from all participating vehicles and individual characteristics from each vehicle to establish a personalized learning mechanism. This enables each vehicle's model to learn features from others while preserving its personalized characteristics, thereby outperforming globally shared models trained in general FL. Extensive experiments demonstrate that pFedLVM outperforms the existing state-of-the-art approaches.

cs.RO↗

LLM-NEO: Parameter Efficient Knowledge Distillation for Large Language Models

Knowledge distillation (KD) has been a predominant method for compressing Large Language Models (LLMs). In this paper, we first revisit KD and Low-Rank Adaption (LoRA) and demonstrate that they follow the same paradigm. Inspired by this observation, we propose a parameter-efficient knowledge distillation method, LLM-NEO, which integrates LoRA into KD to improve the efficiency of knowledge transfer. After that, we summarize some valuable guidelines for the hyperparameters in LLM-NEO. Experimental results on compressing Llama 2 and Llama 3.2 show that LLM-NEO outperforms various baselines. Further analysis demonstrates the robustness of the proposed LLM-NEO on variants of LoRA. The code and trained models are available at [Github](https://github.com/yang3121099/LLM-Neo).

cs.CL↗

Unveiling the Power of Complex-Valued Transformers in Wireless Communications

Utilizing complex-valued neural networks (CVNNs) in wireless communication tasks has received growing attention for their ability to provide natural and effective representation of complex-valued signals and data. However, existing studies typically employ complex-valued versions of simple neural network architectures. Not only they merely scratch the surface of the extensive range of modern deep learning techniques, theoretical understanding of the superior performance of CVNNs is missing. To this end, this paper aims to fill both the theoretical and practice gap of employing CVNNs in wireless communications. In particular, we provide a comprehensive description on the various operations in CVNNs and theoretically prove that the CVNN requires fewer layers than the real-valued counterpart to achieve a given approximation error of a continuous function. Furthermore, to advance CVNNs in the field of wireless communications, this paper focuses on the transformer model, which represents a more sophisticated deep learning architecture and has been shown to have excellent performance in wireless communications but only in its real-valued form. In this aspect, we propose a fundamental paradigm of complex-valued transformers for wireless communications. Leveraging this structure, we develop customized complex-valued transformers for three representative applications in wireless communications: channel estimation, user activity detection, and precoding design. These applications utilize transformers with varying levels of sophistication and span a variety of tasks, ranging from regression to classification, supervised to unsupervised learning, and specific module design to end-to-end design. Experimental results demonstrate the superior performance of the complex-valued transformers for the above three applications compared to other traditional real-valued neural network-based methods.

eess.SP↗

Label Anything: An Interpretable, High-Fidelity and Prompt-Free Annotator

Learning-based street scene semantic understanding in autonomous driving (AD) has advanced significantly recently, but the performance of the AD model is heavily dependent on the quantity and quality of the annotated training data. However, traditional manual labeling involves high cost to annotate the vast amount of required data for training robust model. To mitigate this cost of manual labeling, we propose a Label Anything Model (denoted as LAM), serving as an interpretable, high-fidelity, and prompt-free data annotator. Specifically, we firstly incorporate a pretrained Vision Transformer (ViT) to extract the latent features. On top of ViT, we propose a semantic class adapter (SCA) and an optimization-oriented unrolling algorithm (OptOU), both with a quite small number of trainable parameters. SCA is proposed to fuse ViT-extracted features to consolidate the basis of the subsequent automatic annotation. OptOU consists of multiple cascading layers and each layer contains an optimization formulation to align its output with the ground truth as closely as possible, though which OptOU acts as being interpretable rather than learning-based blackbox nature. In addition, training SCA and OptOU requires only a single pre-annotated RGB seed image, owing to their small volume of learnable parameters. Extensive experiments clearly demonstrate that the proposed LAM can generate high-fidelity annotations (almost 100% in mIoU) for multiple real-world datasets (i.e., Camvid, Cityscapes, and Apolloscapes) and CARLA simulation dataset.

cs.RO↗

Generalizable Autonomous Driving System across Diverse Adverse Weather Conditions

Various adverse weather conditions pose a significant challenge to autonomous driving (AD) street scene semantic understanding (segmentation). A common strategy is to minimize the disparity between images captured in clear and adverse weather conditions. However, this technique typically relies on utilizing clear image as a reference, which is challenging to obtain in practice. Furthermore, this method typically targets a single adverse condition, and thus perform poorly when confronting a mixture of multiple adverse weather conditions. To address these issues, we introduce a reference-free and Adverse weather-Immune scheme (called AdvImmu) that leverages the invariance of weather conditions over short periods (seconds). Specifically, AdvImmu includes three components: Locally Sequential Mechanism (LSM), Globally Shuffled Mechanism (GSM), and Unfolded Regularizers (URs). LSM leverages temporal correlations between adjacent frames to enhance model performance. GSM is proposed to shuffle LSM segments to prevent overfitting of temporal patterns. URs are the deep unfolding implementation of two proposed regularizers to penalize the model complexity to enhance across-weather generalization. In addition, to overcome the over-reliance on consecutive frame-wise annotations in the training of AdvImmu (typically unavailable in AD scenarios), we incorporate a foundation model named Segment Anything Model (SAM) to assist to annotate frames, and additionally propose a cluster algorithm (denoted as SBICAC) to surmount SAM's category-agnostic issue to generate pseudo-labels. Extensive experiments demonstrate that the proposed AdvImmu outperforms existing state-of-the-art methods by 88.56% in mean Intersection over Union (mIoU).

cs.RO↗

Deep Unfolding Beamforming and Power Control Designs for Multi-Port Matching Networks

The key technologies of sixth generation (6G), such as ultra-massive multiple-input multiple-output (MIMO), enable intricate interactions between antennas and wireless propagation environments. As a result, it becomes necessary to develop joint models that encompass both antennas and wireless propagation channels. To achieve this, we utilize the multi-port communication theory, which considers impedance matching among the source, transmission medium, and load to facilitate efficient power transfer. Specifically, we first investigate the impact of insertion loss, mutual coupling, and other factors on the performance of multi-port matching networks. Next, to further improve system performance, we explore two important deep unfolding designs for the multi-port matching networks: beamforming and power control, respectively. For the hybrid beamforming, we develop a deep unfolding framework, i.e., projected gradient descent (PGD)-Net based on unfolding projected gradient descent. For the power control, we design a deep unfolding network, graph neural network (GNN) aided alternating optimization (AO)Net, which considers the interaction between different ports in optimizing power allocation. Numerical results verify the necessity of considering insertion loss in the dynamic metasurface antenna (DMA) performance analysis. Besides, the proposed PGD-Net based hybrid beamforming approaches approximate the conventional model-based algorithm with very low complexity. Moreover, our proposed power control scheme has a fast run time compared to the traditional weighted minimum mean squared error (WMMSE) method.

cs.IT↗

Fast-Convergent and Communication-Alleviated Heterogeneous Hierarchical Federated Learning in Autonomous Driving

Street Scene Semantic Understanding (denoted as TriSU) is a complex task for autonomous driving (AD). However, inference model trained from data in a particular geographical region faces poor generalization when applied in other regions due to inter-city data domain-shift. Hierarchical Federated Learning (HFL) offers a potential solution for improving TriSU model generalization by collaborative privacy-preserving training over distributed datasets from different cities. Unfortunately, it suffers from slow convergence because data from different cities are with disparate statistical properties. Going beyond existing HFL methods, we propose a Gaussian heterogeneous HFL algorithm (FedGau) to address inter-city data heterogeneity so that convergence can be accelerated. In the proposed FedGau algorithm, both single RGB image and RGB dataset are modelled as Gaussian distributions for aggregation weight design. This approach not only differentiates each RGB image by respective statistical distribution, but also exploits the statistics of dataset from each city in addition to the conventionally considered data volume. With the proposed approach, the convergence is accelerated by 35.5\%-40.6\% compared to existing state-of-the-art (SOTA) HFL methods. On the other hand, to reduce the involved communication resource, we further introduce a novel performance-aware adaptive resource scheduling (AdapRS) policy. Unlike the traditional static resource scheduling policy that exchanges a fixed number of models between two adjacent aggregations, AdapRS adjusts the number of model aggregation at different levels of HFL so that unnecessary communications are minimized. Extensive experiments demonstrate that AdapRS saves 29.65\% communication overhead compared to conventional static resource scheduling policy while maintaining almost the same performance.

cs.LG↗

Revisiting Trace Norm Minimization for Tensor Tucker Completion: A Direct Multilinear Rank Learning Approach

To efficiently express tensor data using the Tucker format, a critical task is to minimize the multilinear rank such that the model would not be over-flexible and lead to overfitting. Due to the lack of rank minimization tools in tensor, existing works connect Tucker multilinear rank minimization to trace norm minimization of matrices unfolded from the tensor data. While these formulations try to exploit the common aim of identifying the low-dimensional structure of the tensor and matrix, this paper reveals that existing trace norm-based formulations in Tucker completion are inefficient in multilinear rank minimization. We further propose a new interpretation of Tucker format such that trace norm minimization is applied to the factor matrices of the equivalent representation, rather than some matrices unfolded from tensor data. Based on the newly established problem formulation, a fixed point iteration algorithm is proposed, and its convergence is proved. Numerical results are presented to show that the proposed algorithm exhibits significant improved performance in terms of multilinear rank learning and consequently tensor signal recovery accuracy, compared to existing trace norm based Tucker completion methods.

eess.SP↗

Handling Distance Constraint in Movable Antenna Aided Systems: A General Optimization Framework

The movable antenna (MA) is a promising technology to exploit more spatial degrees of freedom for enhancing wireless system performance. However, the MA-aided system introduces the non-convex antenna distance constraints, which poses challenges in the underlying optimization problems. To fill this gap, this paper proposes a general framework for optimizing the MA-aided system under the antenna distance constraints. Specifically, we separate the non-convex antenna distance constraints from the objective function by introducing auxiliary variables. Then, the resulting problem can be efficiently solved under the alternating optimization framework. For the subproblems with respect to the antenna position variables and auxiliary variables, the proposed algorithms are able to obtain at least stationary points without any approximations. To verify the effectiveness of the proposed optimization framework, we present two case studies: capacity maximization and regularized zero-forcing precoding. Simulation results demonstrate the proposed optimization framework outperforms the existing baseline schemes under both cases.

eess.SP↗

FedRC: A Rapid-Converged Hierarchical Federated Learning Framework in Street Scene Semantic Understanding

Street Scene Semantic Understanding (denoted as TriSU) is a crucial but complex task for world-wide distributed autonomous driving (AD) vehicles (e.g., Tesla). Its inference model faces poor generalization issue due to inter-city domain-shift. Hierarchical Federated Learning (HFL) offers a potential solution for improving TriSU model generalization, but suffers from slow convergence rate because of vehicles' surrounding heterogeneity across cities. Going beyond existing HFL works that have deficient capabilities in complex tasks, we propose a rapid-converged heterogeneous HFL framework (FedRC) to address the inter-city data heterogeneity and accelerate HFL model convergence rate. In our proposed FedRC framework, both single RGB image and RGB dataset are modelled as Gaussian distributions in HFL aggregation weight design. This approach not only differentiates each RGB sample instead of typically equalizing them, but also considers both data volume and statistical properties rather than simply taking data quantity into consideration. Extensive experiments on the TriSU task using across-city datasets demonstrate that FedRC converges faster than the state-of-the-art benchmark by 38.7%, 37.5%, 35.5%, and 40.6% in terms of mIoU, mPrecision, mRecall, and mF1, respectively. Furthermore, qualitative evaluations in the CARLA simulation environment confirm that the proposed FedRC framework delivers top-tier performance.

cs.RO↗

Nonparametric Teaching of Implicit Neural Representations

We investigate the learning of implicit neural representation (INR) using an overparameterized multilayer perceptron (MLP) via a novel nonparametric teaching perspective. The latter offers an efficient example selection framework for teaching nonparametrically defined (viz. non-closed-form) target functions, such as image functions defined by 2D grids of pixels. To address the costly training of INRs, we propose a paradigm called Implicit Neural Teaching (INT) that treats INR learning as a nonparametric teaching problem, where the given signal being fitted serves as the target function. The teacher then selects signal fragments for iterative training of the MLP to achieve fast convergence. By establishing a connection between MLP evolution through parameter-based gradient descent and that of function evolution through functional gradient descent in nonparametric teaching, we show for the first time that teaching an overparameterized MLP is consistent with teaching a nonparametric learner. This new discovery readily permits a convenient drop-in of nonparametric teaching algorithms to broadly enhance INR training efficiency, demonstrating 30%+ training time savings across various input modalities.

cs.LG↗

RIS-Aided Cooperative Mobile Edge Computing: Computation Efficiency Maximization via Joint Uplink and Downlink Resource Allocation

In mobile edge computing (MEC) systems, the wireless channel condition is a critical factor affecting both the communication power consumption and computation rate of the offloading tasks. This paper exploits the idea of cooperative transmission and employing reconfigurable intelligent surface (RIS) in MEC to improve the channel condition and maximize computation efficiency (CE). The resulting problem couples various wireless resources in both uplink and downlink, which calls for the joint design of the user association, receive/downlink beamforming vectors, transmit power of users, task partition strategies for local computing and offloading, and uplink/downlink phase shifts at the RIS. To tackle the challenges brought by the combinatorial optimization problem, the group sparsity structure of the beamforming vectors determined by user association is exploited. Furthermore, while the CE does not explicitly depend on the downlink phase shifts, instead of simply finding a feasible solution, we exploit the hidden relationship between them and convert this relationship into an explicit form for optimization. Then the resulting problem is solved via the alternating maximization framework, and the nonconvexity of each subproblem is handled individually. Simulation results show that cooperative transmission and RIS deployment can significantly improve the CE and demonstrate the importance of optimizing the downlink phase shifts with an explicit form.

cs.IT↗

Activity Detection for Massive Connectivity in Cell-free Networks with Unknown Large-scale Fading, Channel Statistics, Noise Variance, and Activity Probability: A Bayesian Approach

Activity detection is an important task in the next generation grant-free multiple access. While there are a number of existing algorithms designed for this purpose, they mostly require precise information about the network, such as large-scale fading coefficients, small-scale fading channel statistics, noise variance at the access points, and user activity probability. Acquiring these information would take a significant overhead and their estimated values might not be accurate. This problem is even more severe in cell-free networks as there are many of these parameters to be acquired. Therefore, this paper sets out to investigate the activity detection problem without the above-mentioned information. In order to handle so many unknown parameters, this paper employs the Bayesian approach, where the unknown variables are endowed with prior distributions which effectively act as regularizations. Together with the likelihood function, a maximum a posteriori (MAP) estimator and a variational inference algorithm are derived. Extensive simulations demonstrate that the proposed methods, even without the knowledge of these system parameters, perform better than existing state-of-the-art methods, such as covariance-based and approximate message passing methods.

cs.LG↗

Learning a Low-Rank Feature Representation: Achieving Better Trade-Off between Stability and Plasticity in Continual Learning

In continual learning, networks confront a trade-off between stability and plasticity when trained on a sequence of tasks. To bolster plasticity without sacrificing stability, we propose a novel training algorithm called LRFR. This approach optimizes network parameters in the null space of the past tasks' feature representation matrix to guarantee the stability. Concurrently, we judiciously select only a subset of neurons in each layer of the network while training individual tasks to learn the past tasks' feature representation matrix in low-rank. This increases the null space dimension when designing network parameters for subsequent tasks, thereby enhancing the plasticity. Using CIFAR-100 and TinyImageNet as benchmark datasets for continual learning, the proposed approach consistently outperforms state-of-the-art methods.

cs.LG↗

Communication Resources Constrained Hierarchical Federated Learning for End-to-End Autonomous Driving

While federated learning (FL) improves the generalization of end-to-end autonomous driving by model aggregation, the conventional single-hop FL (SFL) suffers from slow convergence rate due to long-range communications among vehicles and cloud server. Hierarchical federated learning (HFL) overcomes such drawbacks via introduction of mid-point edge servers. However, the orchestration between constrained communication resources and HFL performance becomes an urgent problem. This paper proposes an optimization-based Communication Resource Constrained Hierarchical Federated Learning (CRCHFL) framework to minimize the generalization error of the autonomous driving model using hybrid data and model aggregation. The effectiveness of the proposed CRCHFL is evaluated in the Car Learning to Act (CARLA) simulation platform. Results show that the proposed CRCHFL both accelerates the convergence rate and enhances the generalization of federated learning autonomous driving model. Moreover, under the same communication resource budget, it outperforms the HFL by 10.33% and the SFL by 12.44%.

cs.RO↗

Overcoming Beam Squint in Dual-Wideband mmWave MIMO Channel Estimation: A Bayesian Multi-Band Sparsity Approach

The beam squint effect, which manifests in different steering matrices in different sub-bands, has been widely considered a challenge in millimeter wave (mmWave) multiinput multi-output (MIMO) channel estimation. Existing methods either require specific forms of the precoding/combining matrix, which restrict their general practicality, or simply ignore the beam squint effect by only making use of a single sub-band for channel estimation. Recognizing that different steering matrices are coupled by the same set of unknown channel parameters, this paper proposes to exploit the common sparsity structure of the virtual channel model so that signals from different subbands can be jointly utilized to enhance the performance of channel estimation. A probabilistic model is built to induce the common sparsity in the spatial domain, and the first-order Taylor expansion is adopted to get rid of the grid mismatch in the dictionaries. To learn the model parameters, a variational expectation-maximization (EM) algorithm is derived, which automatically obtains the balance between the likelihood function and the common sparsity prior information, and is applicable to arbitrary forms of precoding/combining matrices. Simulation results show the superior estimation accuracy of the proposed algorithm over existing methods under different noise powers and system configurations.

eess.SP↗

STAR-RIS-Aided Mobile Edge Computing: Computation Rate Maximization with Binary Amplitude Coefficients

In this paper, simultaneously transmitting and reflecting (STAR) reconfigurable intelligent surface (RIS) is investigated in the multi-user mobile edge computing (MEC) system to improve the computation rate. Compared with traditional RIS-aided MEC, STAR-RIS extends the service coverage from half-space to full-space and provides new flexibility for improving the computation rate for end users. However, the STAR-RIS-aided MEC system design is a challenging problem due to the non-smooth and non-convex binary amplitude coefficients with coupled phase shifters. To fill this gap, this paper formulates a computation rate maximization problem via the joint design of the STAR-RIS phase shifts, reflection and transmission amplitude coefficients, the receive beamforming vectors, and energy partition strategies for local computing and offloading. To tackle the discontinuity caused by binary variables, we propose an efficient smoothing-based method to decrease convergence error, in contrast to the conventional penalty-based method, which brings many undesired stationary points and local optima. Furthermore, a fast iterative algorithm is proposed to obtain a stationary point for the joint optimization problem, with each subproblem solved by a low-complexity algorithm, making the proposed design scalable to a massive number of users and STAR-RIS elements. Simulation results validate the strength of the proposed smoothing-based method and show that the proposed fast iterative algorithm achieves a higher computation rate than the conventional method while saving the computation time by at least an order of magnitude. Moreover, the resultant STAR-RIS-aided MEC system significantly improves the computation rate compared to other baseline schemes with conventional reflect-only/transmit-only RIS.

cs.IT↗