Search Results for author: Joonhyuk Kang

Found 22 papers, 7 papers with code

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

no code implementations21 Mar 2024 Sooyeob Jung, Seongah Jeong, Jinkyu Kang, Gyeongrae Im, Sangjae Lee, Mi-Kyung Oh, Joon Gyu Ryu, Joonhyuk Kang

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.

Rate-splitting Multiple Access for Hierarchical HAP-LAP Networks under Limited Fronthaul

no code implementations7 Dec 2023 Jeongbin Kim, Seongah Jeong, Seonghoon Yoo, Woong Son, Joonhyuk Kang

In this correspondence, we propose hierarchical high-altitude platform (HAP)-low-altitude platform (LAP) networks with the aim of maximizing the sum-rate of ground user equipments (UEs).

Quantization

FedSplitX: Federated Split Learning for Computationally-Constrained Heterogeneous Clients

no code implementations23 Oct 2023 Jiyun Shin, JinHyun Ahn, Honggu Kang, Joonhyuk Kang

Foundation models (FMs) have demonstrated remarkable performance in machine learning but demand extensive training data and computational resources.

Federated Learning

On the Temperature of Bayesian Graph Neural Networks for Conformal Prediction

no code implementations17 Oct 2023 Seohyeon Cha, Honggu Kang, Joonhyuk Kang

Building on a recent work that introduced a scaling parameter for constructing valid credible regions from posterior estimate, our study explores the advantages of incorporating a temperature parameter into Bayesian GNNs within CP framework.

Conformal Prediction Uncertainty Quantification +1

Cache-assisted Mobile Edge Computing over Space-Air-Ground Integrated Networks for Extended Reality Applications

no code implementations6 Sep 2023 Seonghoon Yoo, Seongah Jeong, Jeongbin Kim, Joonhyuk Kang

Extended reality-enabled Internet of Things (XRI) provides the new user experience and the sense of immersion by adding virtual elements to the real world through Internet of Things (IoT) devices and emerging 6G technologies.

Edge-computing

NeFL: Nested Federated Learning for Heterogeneous Clients

no code implementations15 Aug 2023 Honggu Kang, Seohyeon Cha, Jinwoo Shin, Jongmyeong Lee, Joonhyuk Kang

Previous studies tackle the system heterogeneity by splitting a model into submodels, but with less degree-of-freedom in terms of model architecture.

Federated Learning

Energy-Efficient Vehicular Edge Computing with One-by-one Access Scheme

no code implementations31 Jan 2023 Youngsu Jang, Seongah Jeong, Joonhyuk Kang

With the advent of ever-growing vehicular applications, vehicular edge computing (VEC) has been a promising solution to augment the computing capacity of future smart vehicles.

Edge-computing Scheduling +1

Marine IoT Systems with Space-Air-Sea Integrated Networks: Hybrid LEO and UAV Edge Computing

no code implementations10 Jan 2023 Sooyeob Jung, Seongah Jeong, Jinkyu Kang, Joonhyuk Kang

Marine Internet of Things (IoT) systems have grown substantially with the development of non-terrestrial networks (NTN) via aerial and space vehicles in the upcoming sixth-generation (6G), thereby assisting environment protection, military reconnaissance, and sea transportation.

Edge-computing Total Energy

Fast-Convergent Federated Learning via Cyclic Aggregation

1 code implementation29 Oct 2022 YoungJoon Lee, Sangwoo Park, Joonhyuk Kang

Federated learning (FL) aims at optimizing a shared global model over multiple edge devices without transmitting (private) data to the central server.

Federated Learning

Security-Preserving Federated Learning via Byzantine-Sensitive Triplet Distance

1 code implementation29 Oct 2022 YoungJoon Lee, Sangwoo Park, Joonhyuk Kang

While being an effective framework of learning a shared model across multiple edge devices, federated learning (FL) is generally vulnerable to Byzantine attacks from adversarial edge devices.

Federated Learning

Compressed Particle-Based Federated Bayesian Learning and Unlearning

no code implementations14 Sep 2022 Jinu Gong, Osvaldo Simeone, Joonhyuk Kang

Conventional frequentist FL schemes are known to yield overconfident decisions.

Quantization

Hybrid UAV-enabled Secure Offloading via Deep Reinforcement Learning

no code implementations16 Aug 2022 Seonghoon Yoo, Seongah Jeong, Joonhyuk Kang

Unmanned aerial vehicles (UAVs) have been actively studied as moving cloudlets to provide application offloading opportunities and to enhance the security level of user equipments (UEs).

reinforcement-learning Reinforcement Learning (RL)

Forget-SVGD: Particle-Based Bayesian Federated Unlearning

no code implementations23 Nov 2021 Jinu Gong, Osvaldo Simeone, Rahif Kassab, Joonhyuk Kang

Variational particle-based Bayesian learning methods have the advantage of not being limited by the bias affecting more conventional parametric techniques.

Bayesian Inference Federated Learning

Bayesian Variational Federated Learning and Unlearning in Decentralized Networks

no code implementations8 Apr 2021 Jinu Gong, Osvaldo Simeone, Joonhyuk Kang

Federated Bayesian learning offers a principled framework for the definition of collaborative training algorithms that are able to quantify epistemic uncertainty and to produce trustworthy decisions.

Federated Learning Variational Inference

End-to-End Fast Training of Communication Links Without a Channel Model via Online Meta-Learning

1 code implementation3 Mar 2020 Sangwoo Park, Osvaldo Simeone, Joonhyuk Kang

The proposed approach is based on a meta-training phase in which the online gradient-based meta-learning of the decoder is coupled with the joint training of the encoder via the transmission of pilots and the use of a feedback link.

Meta-Learning

Cooperative Learning via Federated Distillation over Fading Channels

no code implementations3 Feb 2020 Jin-Hyun Ahn, Osvaldo Simeone, Joonhyuk Kang

Cooperative training methods for distributed machine learning are typically based on the exchange of local gradients or local model parameters.

Signal Processing Distributed, Parallel, and Cluster Computing Information Theory Information Theory

From Learning to Meta-Learning: Reduced Training Overhead and Complexity for Communication Systems

1 code implementation5 Jan 2020 Osvaldo Simeone, Sangwoo Park, Joonhyuk Kang

Machine learning methods adapt the parameters of a model, constrained to lie in a given model class, by using a fixed learning procedure based on data or active observations.

BIG-bench Machine Learning Inductive Bias +1

Meta-Learning to Communicate: Fast End-to-End Training for Fading Channels

1 code implementation22 Oct 2019 Sangwoo Park, Osvaldo Simeone, Joonhyuk Kang

When a channel model is available, learning how to communicate on fading noisy channels can be formulated as the (unsupervised) training of an autoencoder consisting of the cascade of encoder, channel, and decoder.

Meta-Learning

Learning to Demodulate from Few Pilots via Offline and Online Meta-Learning

1 code implementation23 Aug 2019 Sangwoo Park, Hyeryung Jang, Osvaldo Simeone, Joonhyuk Kang

This paper considers an Internet-of-Things (IoT) scenario in which devices sporadically transmit short packets with few pilot symbols over a fading channel.

Meta-Learning

Wireless Federated Distillation for Distributed Edge Learning with Heterogeneous Data

no code implementations5 Jul 2019 Jin-Hyun Ahn, Osvaldo Simeone, Joonhyuk Kang

Cooperative training methods for distributed machine learning typically assume noiseless and ideal communication channels.

BIG-bench Machine Learning Federated Learning

Learning How to Demodulate from Few Pilots via Meta-Learning

1 code implementation6 Mar 2019 Sangwoo Park, Hyeryung Jang, Osvaldo Simeone, Joonhyuk Kang

Consider an Internet-of-Things (IoT) scenario in which devices transmit sporadically using short packets with few pilot symbols.

Meta-Learning

Coded Federated Computing in Wireless Networks with Straggling Devices and Imperfect CSI

no code implementations16 Jan 2019 Sukjong Ha, Jingjing Zhang, Osvaldo Simeone, Joonhyuk Kang

Distributed computing platforms typically assume the availability of reliable and dedicated connections among the processors.

Information Theory Information Theory

Cannot find the paper you are looking for? You can Submit a new open access paper.