Publications

[6] Robust Over-the-Air Federated Learning Under Imperfect CSI

Hwanjin Kim, Hongjae Nam, Jonggyu Jang, Christopher G. Brinton, David J. Love

Under review, 2025-01-01

[5] Fed-ZOE: Communication-Efficient Over-the-Air Federated Learning via Zeroth-Order Estimation

Jonggyu Jang, Hyeonsu Lyu, David J. Love, Hyun Jong Yang

Under review, 2024-11-06

[paper]

[4] Replace-then-Perturb: Targeted Adversarial Attacks With Visual Reasoning for Vision-Language Models

Jonggyu Jang, Hyeonsu Lyu, Jungyeon Koh, Hyun Jong Yang

Under review, 2024-11-01

[paper]

[3] Unveiling Hidden Visual Information: A Reconstruction Attack Against Adversarial Visual Information Hiding

Jonggyu Jang, Hyeonsu Lyu, Seongjin Hwang, Hyun Jong Yang

Under review, 2024-07-20

[paper]

[2] Rethinking Model Inversion Attacks With Patch-Wise Reconstruction

Jonggyu Jang, Hyeonsu Lyu, Hyun Jong Yang

Under review, 2024-05-06

[paper]

[1] Post-Hoc Model Editing with Selective Parameter Modification Using Generalized Influence Functions

Hyeonsu Lyu, Jonggyu Jang, Sehyun Ryu, Hyun Jong Yang

Under review, 2024-05-06

[paper]

[13] Non-iterative Optimization of Trajectory and Radio Resource for Aerial Network

Hyeonsu Lyu^🌻, Jonggyu Jang^🌻, Harim Lee, Hyun Jong Yang

IEEE Transactions on Wireless CommunicationsTWC, 2024-11-24

[paper]

[12] Enhancing Sum-Rate Performance in Constrained Multicell Networks: A Low-Information Exchange Approach

Youjin Kim, Jonggyu Jang, Hyun Jong Yang

IEEE Communications LettersCL, 2024-10-08

[paper]

[11] Age-of-Information-Aware Distributed Task Offloading and Resource Allocation in Mobile Edge Computing Networks

Minwoo Kim^🌻, Jonggyu Jang^🌻, Hyun Jong Yang

IEEE Transactions on Mobile ComputingTMC, 2024-09-02

[paper]

[10] Rethinking DP-SGD in Discrete Domain: Exploring Logistic Distribution in the Realm of signSGD

Jonggyu Jang, Seongjin Hwang, Hyun Jong Yang

International Conference on Machine LearningICML, 2024-07-20

Our study delves into an intriguing question: "Can we find a more efficient substitute for Gaussian noise to secure privacy in DP-signSGD?" We propose an answer with a Logistic mechanism, which conforms to signSGD principles and is interestingly evolved from an exponential mechanism.

[paper] [code]

[9] Noise Variance Optimization in Differential Privacy: A Game-Theoretic Approach Through Per-Instance Differential Privacy

Sehyun Ryu^🌻, Jonggyu Jang^🌻, Hyun Jong Yang

IEEE ACCESS, 2024-05-10

In a nutshell, we propose a per-instance noise variance optimization (NVO) game, framed as a common interest sequential game, and show that the Nash equilibrium (NE) points of it inherently guarantee pDP for all data instances.

[paper]

[8] Distributed Resource Allocation and User Association for Max-Min Fairness in HetNets

Yeongjun Kim, Jonggyu Jang^🌻, Hyun Jong Yang^🌻

IEEE Transactions on Vehicular TechnologyTVT, 2024-02-20

We propose a deep-reinforcement-learning (DRL)-based joint UA and RA scheme to maximize the minimum rate, i.e., max-min fairness (MMF), with highly limited information exchange among the BSs. The proposed DRL algorithm optimizes UA at each BS in a distributed manner to maximize an MMF objective function with only local CSI and without any iterative process.

[paper]

[7] M²SODAI: Multi-Modal Maritime Object Detection Dataset With RGB and Hyperspectral Image Sensors

Jonggyu Jang, Sangwoo Oh, Youjin Kim, Dongmin Seo, Youngchol Choi, Hyun Jong Yang

Conference on Neural Information Processing SystemsNeurIPS, 2023-12-10

We have collected and annotated a new dataset called Multi-Modal Ship and flOating matter Detection in Aerial Images (M2SODAI), which includes synchronized image pairs of RGB and HSI data, along with bounding box labels for nearly 6,000 instances per category.

[paper] [page]

[6] α-Fairness Maximizing User Association in Energy-Constrained Small Cell Networks

Jonggyu Jang, Hyun Jong Yang

IEEE Transactions on Wireless CommunicationsTWC, 2022-09-20

We aim to accelerate the computation of the UA and RA with DRL. The proposed scheme outperforms the optimization-based schemes in the throughput, proportional fairness, and max-min fairness metrics.

[paper]

[5] Deep Learning-Aided User Association and Power Control with Renewable Energy Sources

Jonggyu Jang, Hyun Jong Yang

IEEE Transactions on CommunicationsTCOM, 2022-08-20

This paper tackles the UA and PC optimization for the sum-rate maximization under quality-of-service (QoS) and backhaul constraints. We propose a deep learning-based UA and PC algorithm that can be applied to dynamic HetNets.

[paper] [code]

[4] Recurrent Neural Network-Based User Association and Power Control in Dynamic HetNets

Jonggyu Jang, Hyun Jong Yang

IEEE Transactions on Vehicular TechnologyTVT, 2022-04-20

In pursuit of scalable neural network design, we propose an unsupervised learning-based UA and PC algorithm using a recurrent neural network (RNN).

[paper]

[3] Deep Reinforcement Learning-based Resource Allocation and Power Control in Small Cells with Limited Information Exchange

Jonggyu Jang, Hyun Jong Yang

IEEE Transactions on Vehicular TechnologyTVT, 2020-08-30

The proposed algorithm is self-adaptive in time-varying channels, since it is not divided into training and test phases. We modify the target neural network (TNN) scheme to enhance the sum-rate and the convergence speed.

[paper]

[2] Deep Learning-Based Autonomous Scanning Electron Microscope

Jonggyu Jang, Moohyun Oh, Hyeonsu Lyu, Hyun Jong Yang, Junhee Lee

IEEE/RSJ International Conference on Intelligent Robots and SystemsIROS, 2020-08-10

In this paper, we propose and implement a deep learning-based autonomous SEM machine, which assesses image quality and controls parameters autonomously to get high quality sample images just as if human experts do.

[paper] [video]

[1] Resource Allocation and Power Control in Cooperative Small Cell Networks with Backhaul Constraint

Jonggyu Jang, Hyun Jong Yang, Hyekyung Jwa

IEEE Transactions on Vehicular TechnologyTVT, 2019-11-10

Motivated by the fact that the condition for obtaining the near-global solution with the dual problem approach is rarely satisfied for increasing number of users, we derive explicit first order optimality conditions to obtain a 2-distance ring solution of the primal UA and RA problem, and propose a sequential optimization method. In addition, we propose a PC algorithm based on the first order KKT optimality conditions, in which transmission power of each RB is iteratively updated.

[paper]

[2] Instance-Wise Laplace Mechanism via Deep Reinforcement Learning (Student Abstract)

Sehyun Ryu, Hosung Joo, Jonggyu Jang, Hyun Jong Yang

Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2024-07-20 Oral | 3min

[paper] [video]

[1] Faithful and Fast Influence Function via Advanced Sampling

Jungyeon Koh, Hyeonsu Lyu, Jonggyu Jang, Hyun Jong Yang

ICML Workshop on Mechanistic Interpretability (ICML Wksp), 2024-02-20 Spotlight | top-20%

[paper]

[8] DNN-based Sum-Rate Maximization of Multicell MISO Networks

Youjin Kim, Jonggyu Jang, Hyun Jong Yang

IEEE Asilomar Conference on Signals, Systems, and Computers (ACSSC), 2020-11-10

[paper]

[7] Performance Comparison of SU-and MU-MIMO in 802.11 ax: Delay and Throughput

Yein Heo, Jonggyu Jang, Yeongjun Kim, Hyun Jong Yang

IEEE International Conference on Information and Communication Technology Convergence (ICTC), 2020-10-10

[paper]

[6] Supervised-Learning-Based Resource Allocation in Wireless Networks

Jonggyu Jang, Jung Hwa Park, Hyun Jong Yang

IEEE International Conference on Information and Communication Technology Convergence (ICTC), 2020-10-10

[paper]

[5] Robust deep-learning based autofocus score prediction for scanning electron microscope

Hyun Jong Yang, Moohyun Oh, Jonggyu Jang, Hyeonsu Lyu, Junhee Lee

Microscopy and Microanalysis (M&M), 2020-08-10

[paper]

[4] Deep-learning based autofocus score prediction of scanning electron microscope

Huisoo Kim, Moohyun Oh, Heerang Lee, Jonggyu Jang, Myeung Un Kim, Hyun Jong Yang, Michael Ryoo, Junhee Lee

Microscopy and Microanalysis (M&M), 2019-08-10

[paper]

[3] Learning-based distributed resource allocation in asynchronous multicell networks

Jonggyu Jang, Hyun Jong Yang, Sunghyun Kim

IEEE International Conference on Information and Communication Technology Convergence (ICTC), 2018-08-10

[paper]

[2] Joint user association and resource allocation in small cells with limited backhaul capacity

Jonggyu Jang, Woojin Park, Hyun Jong Yang, Hye Gyung Jwa

IEEE Asiloar Conference on Signals, Systems, and Computers (ACSSC), 2016-11-10

[paper]

[1] Two-Cell Two-Way Relaying with Reduced Interference

Yeongjun Kim, Jonggyu Jang, Hyun Jong Yang

IEEE Vehicle Technology Conference (VTC), 2016-09-10

[paper]