arXiv subjects

Seong-Lyun Kim

Publications and source records attributed to Seong-Lyun Kim.

At least 37 records · Page 2Linked to original sources

arXiv2023

Sequential Semantic Generative Communication for Progressive Text-to-Image Generation

This paper proposes new framework of communication system leveraging promising generation capabilities of multi-modal generative models. Regarding nowadays smart applications, successful communication can be made by conveying the perceptual meaning, which we set as text prompt. Text serves as a suitable semantic representation of image data as it has evolved to instruct an image or generate image through multi-modal techniques, by being interpreted in a manner similar to human cognition. Utilizing text can also reduce the overload compared to transmitting the intact data itself. The transmitter converts objective image to text through multi-model generation process and the receiver reconstructs the image using reverse process. Each word in the text sentence has each syntactic role, responsible for particular piece of information the text contains. For further efficiency in communication load, the transmitter sequentially sends words in priority of carrying the most information until reaches successful communication. Therefore, our primary focus is on the promising design of a communication system based on image-to-text transformation and the proposed schemes for sequentially transmitting word tokens. Our work is expected to pave a new road of utilizing state-of-the-art generative models to real communication systems

eess.SP↗

arXiv2023

SplitAMC: Split Learning for Robust Automatic Modulation Classification

Automatic modulation classification (AMC) is a technology that identifies a modulation scheme without prior signal information and plays a vital role in various applications, including cognitive radio and link adaptation. With the development of deep learning (DL), DL-based AMC methods have emerged, while most of them focus on reducing computational complexity in a centralized structure. This centralized learning-based AMC (CentAMC) violates data privacy in the aspect of direct transmission of client-side raw data. Federated learning-based AMC (FedeAMC) can bypass this issue by exchanging model parameters, but causes large resultant latency and client-side computational load. Moreover, both CentAMC and FedeAMC are vulnerable to large-scale noise occured in the wireless channel between the client and the server. To this end, we develop a novel AMC method based on a split learning (SL) framework, coined SplitAMC, that can achieve high accuracy even in poor channel conditions, while guaranteeing data privacy and low latency. In SplitAMC, each client can benefit from data privacy leakage by exchanging smashed data and its gradient instead of raw data, and has robustness to noise with the help of high scale of smashed data. Numerical evaluations validate that SplitAMC outperforms CentAMC and FedeAMC in terms of accuracy for all SNRs as well as latency.

eess.SP↗

arXiv2022

Enabling the Wireless Metaverse via Semantic Multiverse Communication

Metaverse over wireless networks is an emerging use case of the sixth generation (6G) wireless systems, posing unprecedented challenges in terms of its multi-modal data transmissions with stringent latency and reliability requirements. Towards enabling this wireless metaverse, in this article we propose a novel semantic communication (SC) framework by decomposing the metaverse into human/machine agent-specific semantic multiverses (SMs). An SM stored at each agent comprises a semantic encoder and a generator, leveraging recent advances in generative artificial intelligence (AI). To improve communication efficiency, the encoder learns the semantic representations (SRs) of multi-modal data, while the generator learns how to manipulate them for locally rendering scenes and interactions in the metaverse. Since these learned SMs are biased towards local environments, their success hinges on synchronizing heterogeneous SMs in the background while communicating SRs in the foreground, turning the wireless metaverse problem into the problem of semantic multiverse communication (SMC). Based on this SMC architecture, we propose several promising algorithmic and analytic tools for modeling and designing SMC, ranging from distributed learning and multi-agent reinforcement learning (MARL) to signaling games and symbolic AI.

cs.NI↗

arXiv2022

Enabling AI Quality Control via Feature Hierarchical Edge Inference

With the rise of edge computing, various AI services are expected to be available at a mobile side through the inference based on deep neural network (DNN) operated at the network edge, called edge inference (EI). On the other hand, the resulting AI quality (e.g., mean average precision in objective detection) has been regarded as a given factor, and AI quality control has yet to be explored despite its importance in addressing the diverse demands of different users. This work aims at tackling the issue by proposing a feature hierarchical EI (FHEI), comprising feature network and inference network deployed at an edge server and corresponding mobile, respectively. Specifically, feature network is designed based on feature hierarchy, a one-directional feature dependency with a different scale. A higher scale feature requires more computation and communication loads while it provides a better AI quality. The tradeoff enables FHEI to control AI quality gradually w.r.t. communication and computation loads, leading to deriving a near-to-optimal solution to maximize multi-user AI quality under the constraints of uplink \& downlink transmissions and edge server and mobile computation capabilities. It is verified by extensive simulations that the proposed joint communication-and-computation control on FHEI architecture always outperforms several benchmarks by differentiating each user's AI quality depending on the communication and computation conditions.

eess.SY↗

arXiv2022

Joint Data Deepening-and-Prefetching for Energy-Efficient Edge Learning

The vision of pervasive machine learning (ML) services can be realized by training an ML model on time using real-time data collected by internet of things (IoT) devices. To this end, IoT devices require offloading their data to an edge server in proximity. On the other hand, high dimensional data with a heavy volume causes a significant burden to an IoT device with a limited energy budget. To cope with the limitation, we propose a novel offloading architecture, called joint data deepening and prefetching (JD2P), which is feature-by-feature offloading comprising two key techniques. The first one is data deepening, where each data sample's features are sequentially offloaded in the order of importance determined by the data embedding technique such as principle component analysis (PCA). No more features are offloaded when the features offloaded so far are enough to classify the data, resulting in reducing the amount of offloaded data. The second one is data prefetching, where some features potentially required in the future are offloaded in advance, thus achieving high efficiency via precise prediction and parameter optimization. To verify the effectiveness of JD2P, we conduct experiments using the MNIST and fashion-MNIST dataset. Experimental results demonstrate that the JD2P can significantly reduce the expected energy consumption compared with several benchmarks without degrading learning accuracy.

cs.NI↗

arXiv2022

Over-the-Air Consensus for Distributed Vehicle Platooning Control (Extended version)

A distributed control of vehicle platooning is referred to as distributed consensus (DC) since many autonomous vehicles (AVs) reach a consensus to move as one body with the same velocity and inter-distance. For DC control to be stable, other AVs' real-time position information should be inputted to each AV's controller via vehicle-to-vehicle (V2V) communications. On the other hand, too many V2V links should be simultaneously established and frequently retrained, causing frequent packet loss and longer communication latency. We propose a novel DC algorithm called over-the-air consensus (AirCons), a joint communication-and-control design with two key features to overcome the above limitations. First, exploiting a wireless signal's superposition and broadcasting properties renders all AVs' signals to converge to a specific value proportional to participating AVs' average position without individual V2V channel information. Second, the estimated average position is used to control each AV's dynamics instead of each AV's individual position. Through analytic and numerical studies, the effectiveness of the proposed AirCons designed on the state-of-the-art New Radio architecture is verified by showing a $14.22\%$ control gain compared to the benchmark without the average position.

cs.IT↗

arXiv2022

Differentially Private CutMix for Split Learning with Vision Transformer

Recently, vision transformer (ViT) has started to outpace the conventional CNN in computer vision tasks. Considering privacy-preserving distributed learning with ViT, federated learning (FL) communicates models, which becomes ill-suited due to ViT' s large model size and computing costs. Split learning (SL) detours this by communicating smashed data at a cut-layer, yet suffers from data privacy leakage and large communication costs caused by high similarity between ViT' s smashed data and input data. Motivated by this problem, we propose DP-CutMixSL, a differentially private (DP) SL framework by developing DP patch-level randomized CutMix (DP-CutMix), a novel privacy-preserving inter-client interpolation scheme that replaces randomly selected patches in smashed data. By experiment, we show that DP-CutMixSL not only boosts privacy guarantees and communication efficiency, but also achieves higher accuracy than its Vanilla SL counterpart. Theoretically, we analyze that DP-CutMix amplifies Rényi DP (RDP), which is upper-bounded by its Vanilla Mixup counterpart.

cs.DC↗

arXiv2022

Towards Semantic Communication Protocols: A Probabilistic Logic Perspective

Classical medium access control (MAC) protocols are interpretable, yet their task-agnostic control signaling messages (CMs) are ill-suited for emerging mission-critical applications. By contrast, neural network (NN) based protocol models (NPMs) learn to generate task-specific CMs, but their rationale and impact lack interpretability. To fill this void, in this article we propose, for the first time, a semantic protocol model (SPM) constructed by transforming an NPM into an interpretable symbolic graph written in the probabilistic logic programming language (ProbLog). This transformation is viable by extracting and merging common CMs and their connections while treating the NPM as a CM generator. By extensive simulations, we corroborate that the SPM tightly approximates its original NPM while occupying only 0.02% memory. By leveraging its interpretability and memory-efficiency, we demonstrate several SPM-enabled applications such as SPM reconfiguration for collision-avoidance, as well as comparing different SPMs via semantic entropy calculation and storing multiple SPMs to cope with non-stationary environments.

cs.IT↗

arXiv2022

Visual Transformer Meets CutMix for Improved Accuracy, Communication Efficiency, and Data Privacy in Split Learning

This article seeks for a distributed learning solution for the visual transformer (ViT) architectures. Compared to convolutional neural network (CNN) architectures, ViTs often have larger model sizes, and are computationally expensive, making federated learning (FL) ill-suited. Split learning (SL) can detour this problem by splitting a model and communicating the hidden representations at the split-layer, also known as smashed data. Notwithstanding, the smashed data of ViT are as large as and as similar as the input data, negating the communication efficiency of SL while violating data privacy. To resolve these issues, we propose a new form of CutSmashed data by randomly punching and compressing the original smashed data. Leveraging this, we develop a novel SL framework for ViT, coined CutMixSL, communicating CutSmashed data. CutMixSL not only reduces communication costs and privacy leakage, but also inherently involves the CutMix data augmentation, improving accuracy and scalability. Simulations corroborate that CutMixSL outperforms baselines such as parallelized SL and SplitFed that integrates FL with SL.

cs.LG↗

arXiv2022

Two-Stage Deep Anomaly Detection with Heterogeneous Time Series Data

We introduce a data-driven anomaly detection framework using a manufacturing dataset collected from a factory assembly line. Given heterogeneous time series data consisting of operation cycle signals and sensor signals, we aim at discovering abnormal events. Motivated by our empirical findings that conventional single-stage benchmark approaches may not exhibit satisfactory performance under our challenging circumstances, we propose a two-stage deep anomaly detection (TDAD) framework in which two different unsupervised learning models are adopted depending on types of signals. In Stage I, we select anomaly candidates by using a model trained by operation cycle signals; in Stage II, we finally detect abnormal events out of the candidates by using another model, which is suitable for taking advantage of temporal continuity, trained by sensor signals. A distinguishable feature of our framework is that operation cycle signals are exploited first to find likely anomalous points, whereas sensor signals are leveraged to filter out unlikely anomalous points afterward. Our experiments comprehensively demonstrate the superiority over single-stage benchmark approaches, the model-agnostic property, and the robustness to difficult situations.

cs.AI↗

arXiv2021

Communication-Efficient and Personalized Federated Lottery Ticket Learning

The lottery ticket hypothesis (LTH) claims that a deep neural network (i.e., ground network) contains a number of subnetworks (i.e., winning tickets), each of which exhibiting identically accurate inference capability as that of the ground network. Federated learning (FL) has recently been applied in LotteryFL to discover such winning tickets in a distributed way, showing higher accuracy multi-task learning than Vanilla FL. Nonetheless, LotteryFL relies on unicast transmission on the downlink, and ignores mitigating stragglers, questioning scalability. Motivated by this, in this article we propose a personalized and communication-efficient federated lottery ticket learning algorithm, coined CELL, which exploits downlink broadcast for communication efficiency. Furthermore, it utilizes a novel user grouping method, thereby alternating between FL and lottery learning to mitigate stragglers. Numerical simulations validate that CELL achieves up to 3.6% higher personalized task classification accuracy with 4.3x smaller total communication cost until convergence under the CIFAR-10 dataset.

cs.LG↗

arXiv2021

Exploiting User Mobility for WiFi RTT Positioning: A Geometric Approach

Recently, round-trip time (RTT) measured by a fine-timing measurement protocol has received great attention in the area of WiFi positioning. It provides an acceptable ranging accuracy in favorable environments when a line-of-sight (LOS) path exists. Otherwise, a signal is detoured along with non-LOS paths, making the resultant ranging results different from the ground-truth, called an RTT bias, which is the main reason for poor positioning performance. To address it, we aim at leveraging the user mobility trajectory detected by a smartphone's inertial measurement units, called pedestrian dead reckoning (PDR). Specifically, PDR provides the geographic relation among adjacent locations, guiding the resultant positioning estimates' sequence not to deviate from the user trajectory. To this end, we describe their relations as multiple geometric equations, enabling us to render a novel positioning algorithm with acceptable accuracy. Depending on the mobility pattern being linear or arbitrary, we develop different algorithms divided into two phases. First, we can jointly estimate an RTT bias of each AP and the user's step length by leveraging the geometric relation mentioned above. It enables us to construct a user's relative trajectory defined on the concerned AP's local coordinate system. Second, we align every AP's relative trajectory into a single one, called trajectory alignment, equivalent to transformation to the global coordinate system. As a result, we can estimate the sequence of the user's absolute locations from the aligned trajectory. Various field experiments extensively verify the proposed algorithm's effectiveness that the average positioning error is approximately 0.369 (m) and 1.705 (m) in LOS and NLOS environments, respectively.

cs.NI↗

arXiv2021

Most Efficient Sensor Network Protocol for a Permanent Natural Disaster Monitoring System

To minimize enormous havoc from disasters, permanent environment monitoring is necessarily required. Thus we propose a novel energy management protocol for energy harvesting wireless sensor networks (EH-WSNs), named the adaptive sensor node management protocol (ASMP). The proposed protocol makes system components to systematically control their performance to conserve the energy. Through this protocol, sensor nodes autonomously activate an additional energy conservation algorithm. ASMP embeds three sampling algorithms. For the optimized environment sampling, we proposed the adaptive sampling algorithm for monitoring (ASA-m). ASA-m estimates the expected time period to occur meaningful change. The meaningful change refers to the distance between two target data for the monitoring QoS. Therefore, ASA-m merely gathers the data the system demands. The continuous adaptive sampling algorithm (CASA) solves the problem to be continuously decreasing energy despite of ASA-m. When the monitored environment shows a linear trend property, the sensor node in CASA rests a sampling process, and the server generates predicted data at the estimated time slot. For guaranteeing the self-sustainability, ASMP uses the recoverable adaptive sampling algorithm (RASA). RASA makes consumed energy smaller than harvested energy by utilizing the predicted data. RASA recharges the energy of the sensor node. Through this method, ASMP achieves both energy conservation and service quality.

cs.NI↗

arXiv2021

Mean-Field Game-Theoretic Edge Caching

In this book chapter, we study a problem of distributed content caching in an ultra-dense edge caching network (UDCN), in which a large number of small base stations (SBSs) prefetch popular files to cope with the ever-growing user demand in 5G and beyond. In a UDCN, even a small misprediction of user demand may render a large amount of prefetched data obsolete. Furtherproacmore, the interference variance is high due to the short inter-SBS distances, making it difficult to quantify data downloading rates. Lastly, since the caching decision of each SBS interacts with those of all other SBSs, the problem complexity of exponentially increases with the number of SBSs, which is unfit for UDCNs. To resolve such challenging issues while reflecting time-varying and location-dependent user demand, we leverage mean-field game (MFG) theory through which each SBS interacts only with a single virtual SBS whose state is drawn from the state distribution of the entire SBS population, i.e., mean-field (MF) distribution. This MF approximation asymptotically guarantees achieving the epsilon Nash equilibrium as the number of SBSs approaches infinity. To describe such an MFG-theoretic caching framework, this chapter aims to provide a brief review of MFG, and demonstrate its effectiveness for UDCNs.

cs.IT↗

arXiv2020

Federated Knowledge Distillation

Distributed learning frameworks often rely on exchanging model parameters across workers, instead of revealing their raw data. A prime example is federated learning that exchanges the gradients or weights of each neural network model. Under limited communication resources, however, such a method becomes extremely costly particularly for modern deep neural networks having a huge number of model parameters. In this regard, federated distillation (FD) is a compelling distributed learning solution that only exchanges the model outputs whose dimensions are commonly much smaller than the model sizes (e.g., 10 labels in the MNIST dataset). The goal of this chapter is to provide a deep understanding of FD while demonstrating its communication efficiency and applicability to a variety of tasks. To this end, towards demystifying the operational principle of FD, the first part of this chapter provides a novel asymptotic analysis for two foundational algorithms of FD, namely knowledge distillation (KD) and co-distillation (CD), by exploiting the theory of neural tangent kernel (NTK). Next, the second part elaborates on a baseline implementation of FD for a classification task, and illustrates its performance in terms of accuracy and communication efficiency compared to FL. Lastly, to demonstrate the applicability of FD to various distributed learning tasks and environments, the third part presents two selected applications, namely FD over asymmetric uplink-and-downlink wireless channels and FD for reinforcement learning.

cs.LG↗

arXiv2020

Communication-Efficient and Distributed Learning Over Wireless Networks: Principles and Applications

Machine learning (ML) is a promising enabler for the fifth generation (5G) communication systems and beyond. By imbuing intelligence into the network edge, edge nodes can proactively carry out decision-making, and thereby react to local environmental changes and disturbances while experiencing zero communication latency. To achieve this goal, it is essential to cater for high ML inference accuracy at scale under time-varying channel and network dynamics, by continuously exchanging fresh data and ML model updates in a distributed way. Taming this new kind of data traffic boils down to improving the communication efficiency of distributed learning by optimizing communication payload types, transmission techniques, and scheduling, as well as ML architectures, algorithms, and data processing methods. To this end, this article aims to provide a holistic overview of relevant communication and ML principles, and thereby present communication-efficient and distributed learning frameworks with selected use cases.

cs.LG↗

arXiv2020

Mix2FLD: Downlink Federated Learning After Uplink Federated Distillation With Two-Way Mixup

This letter proposes a novel communication-efficient and privacy-preserving distributed machine learning framework, coined Mix2FLD. To address uplink-downlink capacity asymmetry, local model outputs are uploaded to a server in the uplink as in federated distillation (FD), whereas global model parameters are downloaded in the downlink as in federated learning (FL). This requires a model output-to-parameter conversion at the server, after collecting additional data samples from devices. To preserve privacy while not compromising accuracy, linearly mixed-up local samples are uploaded, and inversely mixed up across different devices at the server. Numerical evaluations show that Mix2FLD achieves up to 16.7% higher test accuracy while reducing convergence time by up to 18.8% under asymmetric uplink-downlink channels compared to FL.

cs.LG↗

arXiv2020

XOR Mixup: Privacy-Preserving Data Augmentation for One-Shot Federated Learning

User-generated data distributions are often imbalanced across devices and labels, hampering the performance of federated learning (FL). To remedy to this non-independent and identically distributed (non-IID) data problem, in this work we develop a privacy-preserving XOR based mixup data augmentation technique, coined XorMixup, and thereby propose a novel one-shot FL framework, termed XorMixFL. The core idea is to collect other devices' encoded data samples that are decoded only using each device's own data samples. The decoding provides synthetic-but-realistic samples until inducing an IID dataset, used for model training. Both encoding and decoding procedures follow the bit-wise XOR operations that intentionally distort raw samples, thereby preserving data privacy. Simulation results corroborate that XorMixFL achieves up to 17.6% higher accuracy than Vanilla FL under a non-IID MNIST dataset.

cs.LG↗