arXiv subjects

Joonhyuk Kang

Publications and source records attributed to Joonhyuk Kang.

At least 37 records · Page 2Linked to original sources

arXiv2025

CG-FKAN: Compressed-Grid Federated Kolmogorov-Arnold Networks for Communication Constrained Environment

Federated learning (FL), widely used in privacy-critical applications, suffers from limited interpretability, whereas Kolmogorov-Arnold Networks (KAN) address this limitation via learnable spline functions. However, existing FL studies applying KAN overlook the communication overhead introduced by grid extension, which is essential for modeling complex functions. In this letter, we propose CG-FKAN, which compresses extended grids by sparsifying and transmitting only essential coefficients under a communication budget. Experiments show that CG-FKAN achieves up to 13.6% lower RMSE than fixed-grid KAN in communication-constrained settings. In addition, we derive a theoretical upper bound on its approximation error.

cs.LG↗

arXiv2025

Multi-Rate Task-Oriented Communication for Multi-Edge Cooperative Inference

The integration of artificial intelligence (AI) with the Internet of Things (IoT) enables task-oriented communication for multi-edge cooperative inference system, where edge devices transmit extracted features of local sensory data to an edge server to perform AI-driven tasks. However, the privacy concerns and limited communication bandwidth pose fundamental challenges, since simultaneous transmission of extracted features with a single fixed compression ratio from all devices leads to severe inefficiency in communication resource utilization. To address this challenge, we propose a framework that dynamically adjusts the code rate in feature extraction based on its importance to the downstream inference task by adopting a rate-adaptive quantization (RAQ) scheme. Furthermore, to select the code rate for each edge device under limited bandwidth constraint, a dynamic programming (DP) approach is leveraged to allocate the code rate across discrete code rate options. Experiments on multi-view datasets demonstrate that the proposed frameworks significantly outperform the frameworks using fixed-rate quantization, achieving a favorable balance between communication efficiency and inference performance under limited bandwidth conditions.

eess.SP↗

arXiv2025

Embedding Byzantine Fault Tolerance into Federated Learning via Consistency Scoring

Given sufficient data from multiple edge devices, federated learning (FL) enables training a shared model without transmitting private data to the central server. However, FL is generally vulnerable to Byzantine attacks from compromised edge devices, which can significantly degrade the model performance. In this work, we propose an intuitive plugin that seamlessly embeds Byzantine resilience into existing FL methods. The key idea is to generate virtual data samples and evaluate model consistency scores across local updates to effectively filter out compromised updates. By utilizing this scoring mechanism before the aggregation phase, the proposed plugin enables existing FL methods to become robust against Byzantine attacks while maintaining their original benefits. Numerical results on blood cell classification task demonstrate that the proposed plugin provides strong Byzantine resilience. In detail, plugin-attached FedAvg achieves over 89.6% test accuracy under 30% targeted attacks (vs.19.5% w/o plugin) and maintains 65-70% test accuracy under untargeted attacks (vs.17-19% w/o plugin).

cs.LG↗

arXiv2025

A Unified Benchmark of Federated Learning with Kolmogorov-Arnold Networks for Medical Imaging

Federated Learning (FL) enables model training across decentralized devices without sharing raw data, thereby preserving privacy in sensitive domains like healthcare. In this paper, we evaluate Kolmogorov-Arnold Networks (KAN) architectures against traditional MLP across six state-of-the-art FL algorithms on a blood cell classification dataset. Notably, our experiments demonstrate that KAN can effectively replace MLP in federated environments, achieving superior performance with simpler architectures. Furthermore, we analyze the impact of key hyperparameters-grid size and network architecture-on KAN performance under varying degrees of Non-IID data distribution. In addition, our ablation studies reveal that optimizing KAN width while maintaining minimal depth yields the best performance in federated settings. As a result, these findings establish KAN as a promising alternative for privacy-preserving medical imaging applications in distributed healthcare. To the best of our knowledge, this is the first comprehensive benchmark of KAN in FL settings for medical imaging task.

cs.LG↗

arXiv2025

Improving Generalizability of Kolmogorov-Arnold Networks via Error-Correcting Output Codes

Kolmogorov-Arnold Networks (KAN) offer universal function approximation using univariate spline compositions without nonlinear activations. In this work, we integrate Error-Correcting Output Codes (ECOC) into the KAN framework to transform multi-class classification into multiple binary tasks, improving robustness via Hamming distance decoding. Our proposed KAN with ECOC framework outperforms vanilla KAN on a challenging blood cell classification dataset, achieving higher accuracy across diverse hyperparameter settings. Ablation studies further confirm that ECOC consistently enhances performance across FastKAN and FasterKAN variants. These results demonstrate that ECOC integration significantly boosts KAN generalizability in critical healthcare AI applications. To the best of our knowledge, this is the first work of ECOC with KAN for enhancing multi-class medical image classification performance.

cs.LG↗

arXiv2025

Energy-Efficient Secure Communications via Joint Optimization of UAV Trajectory and Movable-Antenna Array Beamforming

This paper investigates the potential of unmanned aerial vehicles (UAVs) equipped with movable-antenna (MA) arrays to strengthen security in wireless communication systems. We propose a novel framework that jointly optimizes the UAV trajectory and the reconfigurable beamforming of the MA array to maximize secrecy energy efficiency, while ensuring reliable communication with legitimate users. By exploiting the spatial degrees of freedom enabled by the MA array, the system can form highly directional beams and deep nulls, thereby significantly improving physical layer security. Numerical results demonstrate that the proposed approach achieves superior secrecy energy efficiency, attributed to the enhanced spatial flexibility provided by the movable antenna architecture.

eess.SP↗

arXiv2025

Debunking Optimization Myths in Federated Learning for Medical Image Classification

Federated Learning (FL) is a collaborative learning method that enables decentralized model training while preserving data privacy. Despite its promise in medical imaging, recent FL methods are often sensitive to local factors such as optimizers and learning rates, limiting their robustness in practical deployments. In this work, we revisit vanilla FL to clarify the impact of edge device configurations, benchmarking recent FL methods on colorectal pathology and blood cell classification task. We numerically show that the choice of local optimizer and learning rate has a greater effect on performance than the specific FL method. Moreover, we find that increasing local training epochs can either enhance or impair convergence, depending on the FL method. These findings indicate that appropriate edge-specific configuration is more crucial than algorithmic complexity for achieving effective FL.

cs.LG↗

arXiv2025

GeFL: Model-Agnostic Federated Learning with Generative Models

Federated learning (FL) is a distributed training paradigm that enables collaborative learning across clients without sharing local data, thereby preserving privacy. However, the increasing scale and complexity of modern deep models often exceed the computational or memory capabilities of edge devices. Furthermore, clients may be constrained to use heterogeneous model architectures due to hardware variability (e.g., ASICs, FPGAs) or proprietary requirements that prevent the disclosure or modification of local model structures. These practical considerations motivate the need for model-heterogeneous FL, where clients participate using distinct model architectures. In this work, we propose Generative Model-Aided Federated Learning (GeFL), a framework that enables cross-client knowledge sharing via a generative model trained in a federated manner. This generative model captures global data semantics and facilitates local training without requiring model homogeneity across clients. While GeFL achieves strong performance, empirical analysis reveals limitations in scalability and potential privacy leakage due to generative sample memorization. To address these concerns, we propose GeFL-F, which utilizes feature-level generative modeling. This approach enhances scalability to large client populations and mitigates privacy risks. Extensive experiments across image classification tasks demonstrate that both GeFL and GeFL-F offer competitive performance in heterogeneous settings. Code is available at [1].

cs.LG↗

arXiv2025

Robust Bayesian Optimization via Localized Online Conformal Prediction

Bayesian optimization (BO) is a sequential approach for optimizing black-box objective functions using zeroth-order noisy observations. In BO, Gaussian processes (GPs) are employed as probabilistic surrogate models to estimate the objective function based on past observations, guiding the selection of future queries to maximize utility. However, the performance of BO heavily relies on the quality of these probabilistic estimates, which can deteriorate significantly under model misspecification. To address this issue, we introduce localized online conformal prediction-based Bayesian optimization (LOCBO), a BO algorithm that calibrates the GP model through localized online conformal prediction (CP). LOCBO corrects the GP likelihood based on predictive sets produced by LOCBO, and the corrected GP likelihood is then denoised to obtain a calibrated posterior distribution on the objective function. The likelihood calibration step leverages an input-dependent calibration threshold to tailor coverage guarantees to different regions of the input space. Under minimal noise assumptions, we provide theoretical performance guarantees for LOCBO's iterates that hold for the unobserved objective function. These theoretical findings are validated through experiments on synthetic and real-world optimization tasks, demonstrating that LOCBO consistently outperforms state-of-the-art BO algorithms in the presence of model misspecification.

cs.LG↗

arXiv2025

Revisit the Stability of Vanilla Federated Learning Under Diverse Conditions

Federated Learning (FL) is a distributed machine learning paradigm enabling collaborative model training across decentralized clients while preserving data privacy. In this paper, we revisit the stability of the vanilla FedAvg algorithm under diverse conditions. Despite its conceptual simplicity, FedAvg exhibits remarkably stable performance compared to more advanced FL techniques. Our experiments assess the performance of various FL methods on blood cell and skin lesion classification tasks using Vision Transformer (ViT). Additionally, we evaluate the impact of different representative classification models and analyze sensitivity to hyperparameter variations. The results consistently demonstrate that, regardless of dataset, classification model employed, or hyperparameter settings, FedAvg maintains robust performance. Given its stability, robust performance without the need for extensive hyperparameter tuning, FedAvg is a safe and efficient choice for FL deployments in resource-constrained hospitals handling medical data. These findings underscore the enduring value of the vanilla FedAvg approach as a trusted baseline for clinical practice.

cs.LG↗

arXiv2025

TQ-DiT: Efficient Time-Aware Quantization for Diffusion Transformers

Diffusion transformers (DiTs) combine transformer architectures with diffusion models. However, their computational complexity imposes significant limitations on real-time applications and sustainability of AI systems. In this study, we aim to enhance the computational efficiency through model quantization, which represents the weights and activation values with lower precision. Multi-region quantization (MRQ) is introduced to address the asymmetric distribution of network values in DiT blocks by allocating two scaling parameters to sub-regions. Additionally, time-grouping quantization (TGQ) is proposed to reduce quantization error caused by temporal variation in activations. The experimental results show that the proposed algorithm achieves performance comparable to the original full-precision model with only a 0.29 increase in FID at W8A8. Furthermore, it outperforms other baselines at W6A6, thereby confirming its suitability for low-bit quantization. These results highlight the potential of our method to enable efficient real-time generative models.

cs.LG↗

arXiv2025

Calibrating Wireless AI via Meta-Learned Context-Dependent Conformal Prediction

Modern software-defined networks, such as Open Radio Access Network (O-RAN) systems, rely on artificial intelligence (AI)-powered applications running on controllers interfaced with the radio access network. To ensure that these AI applications operate reliably at runtime, they must be properly calibrated before deployment. A promising and theoretically grounded approach to calibration is conformal prediction (CP), which enhances any AI model by transforming it into a provably reliable set predictor that provides error bars for estimates and decisions. CP requires calibration data that matches the distribution of the environment encountered during runtime. However, in practical scenarios, network controllers often have access only to data collected under different contexts -- such as varying traffic patterns and network conditions -- leading to a mismatch between the calibration and runtime distributions. This paper introduces a novel methodology to address this calibration-test distribution shift. The approach leverages meta-learning to develop a zero-shot estimator of distribution shifts, relying solely on contextual information. The proposed method, called meta-learned context-dependent weighted conformal prediction (ML-WCP), enables effective calibration of AI applications without requiring data from the current context. Additionally, it can incorporate data from multiple contexts to further enhance calibration reliability.

eess.SP↗

arXiv2025

Rate-Adaptive Quantization: A Multi-Rate Codebook Adaptation for Vector Quantization-based Generative Models

Learning discrete representations with vector quantization (VQ) has emerged as a powerful approach in various generative models. However, most VQ-based models rely on a single, fixed-rate codebook, requiring extensive retraining for new bitrates or efficiency requirements. We introduce Rate-Adaptive Quantization (RAQ), a multi-rate codebook adaptation framework for VQ-based generative models. RAQ applies a data-driven approach to generate variable-rate codebooks from a single baseline VQ model, enabling flexible tradeoffs between compression and reconstruction fidelity. Additionally, we provide a simple clustering-based procedure for pre-trained VQ models, offering an alternative when retraining is infeasible. Our experiments show that RAQ performs effectively across multiple rates, often outperforming conventional fixed-rate VQ baselines. By enabling a single system to seamlessly handle diverse bitrate requirements, RAQ extends the adaptability of VQ-based generative models and broadens their applicability to data compression, reconstruction, and generation tasks.

cs.LG↗

arXiv2025

ROK Defense M&S in the Age of Hyperscale AI: Concepts, Challenges, and Future Directions

Integrating hyperscale AI into national defense M&S(Modeling and Simulation), under the expanding IoMDT(Internet of Military Defense Things) framework, is crucial for boosting strategic and operational readiness. We examine how IoMDT-driven hyperscale AI can provide high accuracy, speed, and the ability to simulate complex, interconnected battlefield scenarios in defense M&S. Countries like the United States and China are leading the adoption of these technologies, with varying levels of success. However, realizing the full potential of hyperscale AI requires overcoming challenges such as closed networks, sparse or long-tail data, complex decision-making processes, and a shortage of experts. Future directions highlight the need to adopt domestic foundation models, expand GPU/NPU investments, leverage large tech services, and employ open source solutions. These efforts will enhance national security, maintain a competitive edge, and spur broader technological and economic growth. With this blueprint, the Republic of Korea can strengthen its defense posture and stay ahead of emerging threats in modern warfare.

eess.SP↗

arXiv2024

NeFL: Nested Model Scaling for Federated Learning with System Heterogeneous Clients

Federated learning (FL) enables distributed training while preserving data privacy, but stragglers-slow or incapable clients-can significantly slow down the total training time and degrade performance. To mitigate the impact of stragglers, system heterogeneity, including heterogeneous computing and network bandwidth, has been addressed. While previous studies have addressed system heterogeneity by splitting models into submodels, they offer limited flexibility in model architecture design, without considering potential inconsistencies arising from training multiple submodel architectures. We propose nested federated learning (NeFL), a generalized framework that efficiently divides deep neural networks into submodels using both depthwise and widthwise scaling. To address the inconsistency arising from training multiple submodel architectures, NeFL decouples a subset of parameters from those being trained for each submodel. An averaging method is proposed to handle these decoupled parameters during aggregation. NeFL enables resource-constrained devices to effectively participate in the FL pipeline, facilitating larger datasets for model training. Experiments demonstrate that NeFL achieves performance gain, especially for the worst-case submodel compared to baseline approaches (7.63% improvement on CIFAR-100). Furthermore, NeFL aligns with recent advances in FL, such as leveraging pre-trained models and accounting for statistical heterogeneity. Our code is available online.

cs.LG↗

arXiv2024

Enhancing Battlefield Awareness: An Aerial RIS-assisted ISAC System with Deep Reinforcement Learning

This paper considers a joint communication and sensing technique for enhancing situational awareness in practical battlefield scenarios. In particular, we propose an aerial reconfigurable intelligent surface (ARIS)-assisted integrated sensing and communication (ISAC) system consisting of a single access point (AP), an ARIS, multiple users, and a sensing target. With deep reinforcement learning (DRL), we jointly optimize the transmit beamforming of the AP, the RIS phase shifts, and the trajectory of the ARIS under signal-to-interference-noise ratio (SINR) constraints. Numerical results demonstrate that the proposed technique outperforms the conventional benchmark schemes by suppressing the self-interference and clutter echo signals or optimizing the RIS phase shifts.

eess.SY↗

arXiv2024

Reliable Sub-Nyquist Spectrum Sensing via Conformal Risk Control

Detecting occupied subbands is a key task for wireless applications such as unlicensed spectrum access. Recently, detection methods were proposed that extract per-subband features from sub-Nyquist baseband samples and then apply thresholding mechanisms based on held-out data. Such existing solutions can only provide guarantees in terms of false negative rate (FNR) in the asymptotic regime of large held-out data sets. In contrast, this work proposes a threshold mechanism-based conformal risk control (CRC), a method recently introduced in statistics. The proposed CRC-based thresholding technique formally meets user-specified FNR constraints, irrespective of the size of the held-out data set. By applying the proposed CRC-based framework to both reconstruction-based and classification-based sub-Nyquist spectrum sensing techniques, it is verified via experimental results that CRC not only provides theoretical guarantees on the FNR but also offers competitive true negative rate (TNR) performance.

eess.SP↗

arXiv2024

LR-FHSS Transceiver for Direct-to-Satellite IoT Communications: Design, Implementation, and Verification

This paper proposes a long range-frequency hopping spread spectrum (LR-FHSS) transceiver design for the Direct-to-Satellite Internet of Things (DtS-IoT) communication system. The DtS-IoT system has recently attracted attention as a promising nonterrestrial network (NTN) solution to provide high-traffic and low-latency data transfer services to IoT devices in global coverage. In particular, this study provides guidelines for the overall DtS-IoT system architecture and design details that conform to the Long Range Wide-Area Network (LoRaWAN). Furthermore, we also detail various DtS-IoT use cases. Considering the multiple low-Earth orbit (LEO) satellites, we developed the LR-FHSS transceiver to improve system efficiency, which is the first attempt in real satellite communication systems using LR-FHSS. Moreover, as an extension of our previous work with perfect synchronization, we applied a robust synchronization scheme against the Doppler effect and co-channel interference (CCI) caused by LEO satellite channel environments, including signal detection for the simultaneous reception of numerous frequency hopping signals and an enhanced soft-output-Viterbi-algorithm (SOVA) for the header and payload receptions. Lastly, we present proof-of-concept implementation and testbeds using an application-specific integrated circuit (ASIC) chipset and a field-programmable gate array (FPGA) that verify the performance of the proposed LR-FHSS transceiver design of DtS-IoT communication systems. The laboratory test results reveal that the proposed LR-FHSS-based framework with the robust synchronization technique can provide wide coverage, seamless connectivity, and high throughput communication links for the realization of future sixth-generation (6G) networks.

eess.SY↗