arXiv subjects

Choong Seon Hong

Publications and source records attributed to Choong Seon Hong.

At least 37 records · Page 2Linked to original sources

arXiv2025

DeepSeek-Inspired Exploration of RL-based LLMs and Synergy with Wireless Networks: A Survey

Reinforcement learning (RL)-based large language models (LLMs), such as ChatGPT, DeepSeek, and Grok-3, have attracted widespread attention for their remarkable capabilities in multimodal data understanding. Meanwhile, the rapid expansion of information services has led to a growing demand for AI-enabled wireless networks. The open-source DeepSeek models are famous for their innovative designs, such as large-scale pure RL and cost-efficient training, which make them well-suited for practical deployment in wireless networks. By integrating DeepSeek-style LLMs with wireless infrastructures, a synergistic opportunity arises: the DeepSeek-style LLMs enhance network optimization with strong reasoning and decision-making abilities, while wireless infrastructure enables the broad deployment of these models. Motivated by this convergence, this survey presents a comprehensive DeepSeek-inspired exploration of RL-based LLMs in the context of wireless networks. We begin by reviewing key techniques behind network optimization to establish a foundation for understanding DeepSeek-style LLM integration. Next, we examine recent advancements in RL-based LLMs, using DeepSeek models as a representative example. Building on this, we explore the synergy between the two domains, highlighting motivations, challenges, and potential solutions. Finally, we highlight emerging directions for integrating LLMs with wireless networks, such as quantum, on-device, and neural-symbolic LLM models, as well as embodied AI agents. Overall, this survey offers a comprehensive examination of the interplay between DeepSeek-style LLMs and wireless networks, demonstrating how these domains can mutually enhance each other to drive innovation.

cs.LG↗

arXiv2025

A Contemporary Survey on Semantic Communications:Theory of Mind, Generative AI, and Deep Joint Source-Channel Coding

Semantic communication is emerging as the next pillar in wireless communication technology due to its transformative capabilities in reducing communication overhead, enhancing robustness, and enabling intelligent information exchange. The most significant obstacle lies in the lack of standardization across various research directions, leading to inconsistencies in interpretation, objectives, and evaluation. In this survey, we provide an in-depth overview of three leading directions in semantic communication, namely Theory of Mind-based semantic communication, Generative AI-driven semantic communication, and Deep Joint Source-Channel Coding (DJSCC)-based semantic communication. These directions have been extensively studied and developed by research institutes worldwide, and their effectiveness continues to improve alongside advances in communication and computing technologies. The ToM-based semantic communication enables communication agents to interact intelligently, infer each other's intentions, and gradually form a shared understanding. The GAI-based semantic communication leverages generative models to create and interpret content beyond traditional compression, allowing flexible semantic encoding and decoding tailored to specific tasks. The DJSCC-based semantic communication direction integrates DL models to jointly optimize the source and channel coding processes for efficient semantic information transfer. Next, we present a detailed survey of existing works under each direction and open research problems in semantic communication. Furthermore, we identify and analyze critical challenges, such as scalability and adaptability, that currently hinder the deployment of semantic communication systems. Finally, we discuss potential research opportunities and future directions such as quantum computing to further enhance the capabilities of semantic communication.

cs.IT↗

arXiv2025

A Deep Incremental Framework for Multi-Service Multi-Modal Devices in NextG AI-RAN Systems

In this paper, we propose a deep incremental framework for efficient RAN management, introducing the Multi-Service-Modal UE (MSMU) system, which enables a single UE to handle eMBB and uRLLC services simultaneously. We formulate an optimization problem integrating traffic demand prediction, route optimization, RAN slicing, service identification, and radio resource management under uncertainty. We decompose it into long-term (L-SP) and short-term (S-SP) subproblems then propose a Transformer model for L-SP optimization, predicting eMBB and uRLLC traffic demands and optimizing routes for RAN slicing. To address non-stationary network traffic with evolving trends and scale variations, we integrate reversible instance normalization (ReVIN) into the forecasting pipeline. For the S-SP, we propose an LSTM model enabling real-time service type identification and resource management, utilizing L-SP predictions. We incorporate continual learning into the S-SP framework to adapt to new service types while preserving prior knowledge. Experimental results demonstrate that our proposed framework achieves up to 46.86% reduction in traffic demand prediction error, 26.70% and 18.79% improvement in PRBs and power estimation, 7.23% higher route selection accuracy, and 7.29% improvement in service identification over the baselines with 95% average accuracy in continual service identification across seven sequential tasks.

cs.NI↗

arXiv2025

Mitigating Domain Shift in Federated Learning via Intra- and Inter-Domain Prototypes

Federated Learning (FL) has emerged as a decentralized machine learning technique, allowing clients to train a global model collaboratively without sharing private data. However, most FL studies ignore the crucial challenge of heterogeneous domains where each client has a distinct feature distribution, which is popular in real-world scenarios. Prototype learning, which leverages the mean feature vectors within the same classes, has become a prominent solution for federated learning under domain shift. However, existing federated prototype learning methods focus soley on inter-domain prototypes and neglect intra-domain perspectives. In this work, we introduce a novel federated prototype learning method, namely I$^2$PFL, which incorporates $\textbf{I}$ntra-domain and $\textbf{I}$nter-domain $\textbf{P}$rototypes, to mitigate domain shift from both perspectives and learn a generalized global model across multiple domains in federated learning. To construct intra-domain prototypes, we propose feature alignment with MixUp-based augmented prototypes to capture the diversity within local domains and enhance the generalization of local features. Additionally, we introduce a reweighting mechanism for inter-domain prototypes to generate generalized prototypes that reduce domain shift while providing inter-domain knowledge across multiple clients. Extensive experiments on the Digits, Office-10, and PACS datasets illustrate the superior performance of our method compared to other baselines.

cs.LG↗

arXiv2025

DD-JSCC: Dynamic Deep Joint Source-Channel Coding for Semantic Communications

Deep Joint Source-Channel Coding (Deep-JSCC) has emerged as a promising semantic communication approach for wireless image transmission by jointly optimizing source and channel coding using deep learning techniques. However, traditional Deep-JSCC architectures employ fixed encoder-decoder structures, limiting their adaptability to varying device capabilities, real-time performance optimization, power constraints and channel conditions. To address these limitations, we propose DD-JSCC: Dynamic Deep Joint Source-Channel Coding for Semantic Communications, a novel encoder-decoder architecture designed for semantic communication systems. Unlike traditional Deep-JSCC models, DD-JSCC is flexible for dynamically adjusting its layer structures in real-time based on transmitter and receiver capabilities, power constraints, compression ratios, and current channel conditions. This adaptability is achieved through a hierarchical layer activation mechanism combined with implicit regularization via sequential randomized training, effectively reducing combinatorial complexity, preventing overfitting, and ensuring consistent feature representations across varying configurations. Simulation results demonstrate that DD-JSCC enhances the performance of image reconstruction in semantic communications, achieving up to 2 dB improvement in Peak Signal-to-Noise Ratio (PSNR) over fixed Deep-JSCC architectures, while reducing training costs by over 40%. The proposed unified framework eliminates the need for multiple specialized models, significantly reducing training complexity and deployment overhead.

cs.NI↗

arXiv2025

Large Language Models-Empowered Wireless Networks: Fundamentals, Architecture, and Challenges

The rapid advancement of wireless networks has resulted in numerous challenges stemming from their extensive demands for quality of service towards innovative quality of experience metrics (e.g., user-defined metrics in terms of sense of physical experience for haptics applications). In the meantime, large language models (LLMs) emerged as promising solutions for many difficult and complex applications/tasks. These lead to a notion of the integration of LLMs and wireless networks. However, this integration is challenging and needs careful attention in design. Therefore, in this article, we present a notion of rational wireless networks powered by \emph{telecom LLMs}, namely, \emph{LLM-native wireless systems}. We provide fundamentals, vision, and a case study of the distributed implementation of LLM-native wireless systems. In the case study, we propose a solution based on double deep Q-learning (DDQN) that outperforms existing DDQN solutions. Finally, we provide open challenges.

cs.NI↗

arXiv2025

Robust Federated Learning on Edge Devices with Domain Heterogeneity

Federated Learning (FL) allows collaborative training while ensuring data privacy across distributed edge devices, making it a popular solution for privacy-sensitive applications. However, FL faces significant challenges due to statistical heterogeneity, particularly domain heterogeneity, which impedes the global mode's convergence. In this study, we introduce a new framework to address this challenge by improving the generalization ability of the FL global model under domain heterogeneity, using prototype augmentation. Specifically, we introduce FedAPC (Federated Augmented Prototype Contrastive Learning), a prototype-based FL framework designed to enhance feature diversity and model robustness. FedAPC leverages prototypes derived from the mean features of augmented data to capture richer representations. By aligning local features with global prototypes, we enable the model to learn meaningful semantic features while reducing overfitting to any specific domain. Experimental results on the Office-10 and Digits datasets illustrate that our framework outperforms SOTA baselines, demonstrating superior performance.

cs.LG↗

arXiv2025

SemSpaceFL: A Collaborative Hierarchical Federated Learning Framework for Semantic Communication in 6G LEO Satellites

The advent of the sixth-generation (6G) wireless networks, enhanced by artificial intelligence, promises ubiquitous connectivity through Low Earth Orbit (LEO) satellites. These satellites are capable of collecting vast amounts of geographically diverse and real-time data, which can be immensely valuable for training intelligent models. However, limited inter-satellite communication and data privacy constraints hinder data collection on a single server for training. Therefore, we propose SemSpaceFL, a novel hierarchical federated learning (HFL) framework for LEO satellite networks, with integrated semantic communication capabilities. Our framework introduces a two-tier aggregation architecture where satellite models are first aggregated at regional gateways before final consolidation at a cloud server, which explicitly accounts for satellite mobility patterns and energy constraints. The key innovation lies in our novel aggregation approach, which dynamically adjusts the contribution of each satellite based on its trajectory and association with different gateways, which ensures stable model convergence despite the highly dynamic nature of LEO constellations. To further enhance communication efficiency, we incorporate semantic encoding-decoding techniques trained through the proposed HFL framework, which enables intelligent data compression while maintaining signal integrity. Our experimental results demonstrate that the proposed aggregation strategy achieves superior performance and faster convergence compared to existing benchmarks, while effectively managing the challenges of satellite mobility and energy limitations in dynamic LEO networks.

cs.IT↗

arXiv2025

Towards Communication-Efficient Adversarial Federated Learning for Robust Edge Intelligence

Federated learning (FL) has gained significant attention for enabling decentralized training on edge networks without exposing raw data. However, FL models remain susceptible to adversarial attacks and performance degradation in non-IID data settings, thus posing challenges to both robustness and accuracy. This paper aims to achieve communication-efficient adversarial federated learning (AFL) by leveraging a pre-trained model to enhance both robustness and accuracy under adversarial attacks and non-IID challenges in AFL. By leveraging the knowledge from a pre-trained model for both clean and adversarial images, we propose a pre-trained model-guided adversarial federated learning (PM-AFL) framework. This framework integrates vanilla and adversarial mixture knowledge distillation to effectively balance accuracy and robustness while promoting local models to learn from diverse data. Specifically, for clean accuracy, we adopt a dual distillation strategy where the class probabilities of randomly paired images, and their blended versions are aligned between the teacher model and the local models. For adversarial robustness, we employ a similar distillation approach but replace clean samples on the local side with adversarial examples. Moreover, by considering the bias between local and global models, we also incorporate a consistency regularization term to ensure that local adversarial predictions stay aligned with their corresponding global clean ones. These strategies collectively enable local models to absorb diverse knowledge from the teacher model while maintaining close alignment with the global model, thereby mitigating overfitting to local optima and enhancing the generalization of the global model. Experiments demonstrate that the PM-AFL-based framework not only significantly outperforms other methods but also maintains communication efficiency.

cs.CV↗

arXiv2025

FedFeat+: A Robust Federated Learning Framework Through Federated Aggregation and Differentially Private Feature-Based Classifier Retraining

In this paper, we propose the FedFeat+ framework, which distinctively separates feature extraction from classification. We develop a two-tiered model training process: following local training, clients transmit their weights and some features extracted from the feature extractor from the final local epochs to the server. The server aggregates these models using the FedAvg method and subsequently retrains the global classifier utilizing the shared features. The classifier retraining process enhances the model's understanding of the holistic view of the data distribution, ensuring better generalization across diverse datasets. This improved generalization enables the classifier to adaptively influence the feature extractor during subsequent local training epochs. We establish a balance between enhancing model accuracy and safeguarding individual privacy through the implementation of differential privacy mechanisms. By incorporating noise into the feature vectors shared with the server, we ensure that sensitive data remains confidential. We present a comprehensive convergence analysis, along with theoretical reasoning regarding performance enhancement and privacy preservation. We validate our approach through empirical evaluations conducted on benchmark datasets, including CIFAR-10, CIFAR-100, MNIST, and FMNIST, achieving high accuracy while adhering to stringent privacy guarantees. The experimental results demonstrate that the FedFeat+ framework, despite using only a lightweight two-layer CNN classifier, outperforms the FedAvg method in both IID and non-IID scenarios, achieving accuracy improvements ranging from 3.92 % to 12.34 % across CIFAR-10, CIFAR-100, and Fashion-MNIST datasets.

cs.CV↗

arXiv2025

Security Risks in Vision-Based Beam Prediction: From Spatial Proxy Attacks to Feature Refinement

The rapid evolution towards the sixth-generation (6G) networks demands advanced beamforming techniques to address challenges in dynamic, high-mobility scenarios, such as vehicular communications. Vision-based beam prediction utilizing RGB camera images emerges as a promising solution for accurate and responsive beam selection. However, reliance on visual data introduces unique vulnerabilities, particularly susceptibility to adversarial attacks, thus potentially compromising beam accuracy and overall network reliability. In this paper, we conduct the first systematic exploration of adversarial threats specifically targeting vision-based mmWave beam selection systems. Traditional white-box attacks are impractical in this context because ground-truth beam indices are inaccessible and spatial dynamics are complex. To address this, we propose a novel black-box adversarial attack strategy, termed Spatial Proxy Attack (SPA), which leverages spatial correlations between user positions and beam indices to craft effective perturbations without requiring access to model parameters or labels. To counteract these adversarial vulnerabilities, we formulate an optimization framework aimed at simultaneously enhancing beam selection accuracy under clean conditions and robustness against adversarial perturbations. We introduce a hybrid deep learning architecture integrated with a dedicated Feature Refinement Module (FRM), designed to systematically filter irrelevant, noisy and adversarially perturbed visual features. Evaluations using standard backbone models such as ResNet-50 and MobileNetV2 demonstrate that our proposed method significantly improves performance, achieving up to an +21.07\% gain in Top-K accuracy under clean conditions and a 41.31\% increase in Top-1 adversarial robustness compared to different baseline models.

cs.NI↗

arXiv2025

Joint Beamforming and Trajectory Optimization for Multi-UAV-Assisted Integrated Sensing and Communication Systems

In this paper, we investigate beamforming design and trajectory optimization for a multi-unmanned aerial vehicle (UAV)-assisted integrated sensing and communication (ISAC) system. The proposed system employs multiple UAVs equipped with dual-functional radar-communication capabilities to simultaneously perform target sensing and provide communication services to users. We formulate a joint optimization problem that aims to maximize the sum rate of users while maintaining target sensing performance through coordinated beamforming and UAV trajectory design. To address this challenging non-convex problem, we develop a block coordinated descent (BCD)-based iterative algorithm that decomposes the original problem into tractable subproblems. Then, the beamforming design problem is addressed using fractional programming, while the UAV trajectory is refined through the deep deterministic policy gradient (DDPG) algorithm. The simulation results demonstrate that the proposed joint optimization approach achieves significant performance improvements in both communication throughput and sensing accuracy compared to conventional, separated designs. We also show that proper coordination of multiple UAVs through optimized trajectories and beamforming patterns can effectively balance the tradeoff between sensing and communication objectives.

cs.NI↗

arXiv2025

CLIP-PING: Boosting Lightweight Vision-Language Models with Proximus Intrinsic Neighbors Guidance

Beyond the success of Contrastive Language-Image Pre-training (CLIP), recent trends mark a shift toward exploring the applicability of lightweight vision-language models for resource-constrained scenarios. These models often deliver suboptimal performance when relying solely on a single image-text contrastive learning objective, spotlighting the need for more effective training mechanisms that guarantee robust cross-modal feature alignment. In this work, we propose CLIP-PING: Contrastive Language-Image Pre-training with Proximus Intrinsic Neighbors Guidance, a novel yet simple and efficient training paradigm designed to boost the performance of lightweight vision-language models with minimal computational overhead and lower data demands. CLIP-PING bootstraps unimodal features extracted from arbitrary pre-trained encoders to obtain intrinsic guidance of proximus neighbor samples, i.e., nearest-neighbor (NN) and cross nearest-neighbor (XNN). We find that extra contrastive supervision from these neighbors substantially boosts cross-modal alignment, enabling lightweight models to learn more generic features with rich semantic diversity. Extensive experiments reveal that CLIP-PING notably surpasses its peers in zero-shot generalization and cross-modal retrieval tasks. Specifically, a 5.5% gain on zero-shot ImageNet1K classification with 10.7% (I2T) and 5.7% (T2I) on Flickr30K retrieval, compared to the original CLIP when using ViT-XS image encoder trained on 3 million (image, text) pairs. Moreover, CLIP-PING showcases a strong transferability under the linear evaluation protocol across several downstream tasks.

cs.CV↗

arXiv2025

Federated Koopman-Reservoir Learning for Large-Scale Multivariate Time-Series Anomaly Detection

The proliferation of edge devices has dramatically increased the generation of multivariate time-series (MVTS) data, essential for applications from healthcare to smart cities. Such data streams, however, are vulnerable to anomalies that signal crucial problems like system failures or security incidents. Traditional MVTS anomaly detection methods, encompassing statistical and centralized machine learning approaches, struggle with the heterogeneity, variability, and privacy concerns of large-scale, distributed environments. In response, we introduce FedKO, a novel unsupervised Federated Learning framework that leverages the linear predictive capabilities of Koopman operator theory along with the dynamic adaptability of Reservoir Computing. This enables effective spatiotemporal processing and privacy preservation for MVTS data. FedKO is formulated as a bi-level optimization problem, utilizing a specific federated algorithm to explore a shared Reservoir-Koopman model across diverse datasets. Such a model is then deployable on edge devices for efficient detection of anomalies in local MVTS streams. Experimental results across various datasets showcase FedKO's superior performance against state-of-the-art methods in MVTS anomaly detection. Moreover, FedKO reduces up to 8x communication size and 2x memory usage, making it highly suitable for large-scale systems.

cs.LG↗

arXiv2025

Machine Learning for Wireless Metaverse: Fundamentals, Use Case, and Future Directions

Today's wireless systems are posing key challenges in terms of quality of service and quality of physical experience. Metaverse has the potential to reshape, transform, and add innovations to the existing wireless systems. A metaverse is a collective virtual open space that can enable wireless systems using digital twins, digital avatars, and interactive experience technologies. Machine learning (ML) is indispensable for modeling twins, avatars, and deploying interactive experience technologies. In this paper, we present the role of ML in enabling metaverse-based wireless systems. We discuss key fundamental concepts for advancing ML in the metaverse-based wireless systems. Moreover, we present a case study of deep reinforcement learning for metaverse sensing. Finally, we discuss the future directions along with potential solutions.

cs.NI↗

arXiv2025

Cross-Modal Prototype based Multimodal Federated Learning under Severely Missing Modality

Multimodal federated learning (MFL) has emerged as a decentralized machine learning paradigm, allowing multiple clients with different modalities to collaborate on training a global model across diverse data sources without sharing their private data. However, challenges, such as data heterogeneity and severely missing modalities, pose crucial hindrances to the robustness of MFL, significantly impacting the performance of global model. The occurrence of missing modalities in real-world applications, such as autonomous driving, often arises from factors like sensor failures, leading knowledge gaps during the training process. Specifically, the absence of a modality introduces misalignment during the local training phase, stemming from zero-filling in the case of clients with missing modalities. Consequently, achieving robust generalization in global model becomes imperative, especially when dealing with clients that have incomplete data. In this paper, we propose $\textbf{Multimodal Federated Cross Prototype Learning (MFCPL)}$, a novel approach for MFL under severely missing modalities. Our MFCPL leverages the complete prototypes to provide diverse modality knowledge in modality-shared level with the cross-modal regularization and modality-specific level with cross-modal contrastive mechanism. Additionally, our approach introduces the cross-modal alignment to provide regularization for modality-specific features, thereby enhancing the overall performance, particularly in scenarios involving severely missing modalities. Through extensive experiments on three multimodal datasets, we demonstrate the effectiveness of MFCPL in mitigating the challenges of data heterogeneity and severely missing modalities while improving the overall performance and robustness of MFL.

cs.LG↗

arXiv2025

QTSeg: A Query Token-Based Dual-Mix Attention Framework with Multi-Level Feature Distribution for Medical Image Segmentation

Medical image segmentation plays a crucial role in assisting healthcare professionals with accurate diagnoses and enabling automated diagnostic processes. Traditional convolutional neural networks (CNNs) often struggle with capturing long-range dependencies, while transformer-based architectures, despite their effectiveness, come with increased computational complexity. Recent efforts have focused on combining CNNs and transformers to balance performance and efficiency, but existing approaches still face challenges in achieving high segmentation accuracy while maintaining low computational costs. Furthermore, many methods underutilize the CNN encoder's capability to capture local spatial information, concentrating primarily on mitigating long-range dependency issues. To address these limitations, we propose QTSeg, a novel architecture for medical image segmentation that effectively integrates local and global information. QTSeg features a dual-mix attention decoder designed to enhance segmentation performance through: (1) a cross-attention mechanism for improved feature alignment, (2) a spatial attention module to capture long-range dependencies, and (3) a channel attention block to learn inter-channel relationships. Additionally, we introduce a multi-level feature distribution module, which adaptively balances feature propagation between the encoder and decoder, further boosting performance. Extensive experiments on five publicly available datasets covering diverse segmentation tasks, including lesion, polyp, breast cancer, cell, and retinal vessel segmentation, demonstrate that QTSeg outperforms state-of-the-art methods across multiple evaluation metrics while maintaining lower computational costs. Our implementation can be found at: https://github.com/tpnam0901/QTSeg (v1.0.0)

cs.CV↗

arXiv2024

Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks

Federated learning (FL) is a distributed training technology that enhances data privacy in mobile edge networks by allowing data owners to collaborate without transmitting raw data to the edge server. However, data heterogeneity and adversarial attacks pose challenges to develop an unbiased and robust global model for edge deployment. To address this, we propose Federated hyBrid Adversarial training and self-adversarial disTillation (FedBAT), a new framework designed to improve both robustness and generalization of the global model. FedBAT seamlessly integrates hybrid adversarial training and self-adversarial distillation into the conventional FL framework from data augmentation and feature distillation perspectives. From a data augmentation perspective, we propose hybrid adversarial training to defend against adversarial attacks by balancing accuracy and robustness through a weighted combination of standard and adversarial training. From a feature distillation perspective, we introduce a novel augmentation-invariant adversarial distillation method that aligns local adversarial features of augmented images with their corresponding unbiased global clean features. This alignment can effectively mitigate bias from data heterogeneity while enhancing both the robustness and generalization of the global model. Extensive experimental results across multiple datasets demonstrate that FedBAT yields comparable or superior performance gains in improving robustness while maintaining accuracy compared to several baselines.

cs.CV↗