Joohyung Lee
YOU?
Author Swipe
View article: Optimizing Client Participation in Communication-Constrained Federated LLM Adaptation with LoRA
Optimizing Client Participation in Communication-Constrained Federated LLM Adaptation with LoRA Open
Federated learning (FL) enables privacy-preserving adaptation of large language models (LLMs) across distributed clients. However, deploying FL in edge environments remains challenging because of the high communication overhead of full-mod…
View article: LPMLN, Weak Constraints, and P-log
LPMLN, Weak Constraints, and P-log Open
LPMLN is a recently introduced formalism that extends answer set programs by adopting the log-linear weight scheme of Markov Logic. This paper investigates the relationships between LPMLN and two other extensions of answer set programs: we…
View article: Fuzzy Propositional Formulas under the Stable Model Semantics
Fuzzy Propositional Formulas under the Stable Model Semantics Open
We define a stable model semantics for fuzzy propositional formulas, which generalizes both fuzzy propositional logic and the stable model semantics of classical propositional formulas. The syntax of the language is the same as the syntax …
View article: LLM+AL: Bridging Large Language Models and Action Languages for Complex Reasoning About Actions
LLM+AL: Bridging Large Language Models and Action Languages for Complex Reasoning About Actions Open
Large Language Models (LLMs) have made significant strides in various intelligent tasks but still struggle with complex action reasoning tasks that require systematic search. To address this limitation, we propose a method that bridges the…
View article: LLM+AL: Bridging Large Language Models and Action Languages for Complex Reasoning about Actions
LLM+AL: Bridging Large Language Models and Action Languages for Complex Reasoning about Actions Open
Large Language Models (LLMs) have made significant strides in various intelligent tasks but still struggle with complex action reasoning tasks that require systematic search. To address this limitation, we propose a method that bridges the…
View article: EdgeGuard: Decentralized Medical Resource Orchestration via Blockchain-Secured Federated Learning in IoMT Networks
EdgeGuard: Decentralized Medical Resource Orchestration via Blockchain-Secured Federated Learning in IoMT Networks Open
The development of medical data and resources has become essential for enhancing patient outcomes and operational efficiency in an age when digital innovation in healthcare is becoming more important. The rapid growth of the Internet of Me…
View article: How Can Incentives and Cut Layer Selection Influence Data Contribution in Split Federated Learning?
How Can Incentives and Cut Layer Selection Influence Data Contribution in Split Federated Learning? Open
To alleviate the training burden in federated learning while enhancing convergence speed, Split Federated Learning (SFL) has emerged as a promising approach by combining the advantages of federated and split learning. However, recent studi…
View article: A Federated Reinforcement Learning Framework via a Committee Mechanism for Resource Management in 5G Networks
A Federated Reinforcement Learning Framework via a Committee Mechanism for Resource Management in 5G Networks Open
This paper proposes a novel decentralized federated reinforcement learning (DFRL) framework that integrates deep reinforcement learning (DRL) with decentralized federated learning (DFL). The DFRL framework boosts efficient virtual instance…
View article: Generative AI-Enabled Energy-Efficient Mobile Augmented Reality in Multi-Access Edge Computing
Generative AI-Enabled Energy-Efficient Mobile Augmented Reality in Multi-Access Edge Computing Open
This paper proposes a novel offloading and super-resolution (SR) control scheme for energy-efficient mobile augmented reality (MAR) in multi-access edge computing (MEC) using SR as a promising generative artificial intelligence (GAI) techn…
View article: Dynamic Bandwidth Slicing in Passive Optical Networks to Empower Federated Learning
Dynamic Bandwidth Slicing in Passive Optical Networks to Empower Federated Learning Open
Federated Learning (FL) is a decentralized machine learning method in which individual devices compute local models based on their data. In FL, devices periodically share newly trained updates with the central server, rather than submittin…
View article: DRL-empowered joint batch size and weighted aggregation adjustment mechanism for federated learning on non-IID data
DRL-empowered joint batch size and weighted aggregation adjustment mechanism for federated learning on non-IID data Open
To address the accuracy degradation as well as prolonged convergence time due to the inherent data heterogeneity among end-devices in federated learning (FL), we introduce the joint batch size and weighted aggregation adjustment problem, w…
View article: Adaptive Dataset Management Scheme for Lightweight Federated Learning in Mobile Edge Computing
Adaptive Dataset Management Scheme for Lightweight Federated Learning in Mobile Edge Computing Open
Federated learning (FL) in mobile edge computing has emerged as a promising machine-learning paradigm in the Internet of Things, enabling distributed training without exposing private data. It allows multiple mobile devices (MDs) to collab…
View article: Deep Reinforcement Learning-Empowered Cost-Effective Federated Video Surveillance Management Framework
Deep Reinforcement Learning-Empowered Cost-Effective Federated Video Surveillance Management Framework Open
Video surveillance systems are integral to bolstering safety and security across multiple settings. With the advent of deep learning (DL), a specialization within machine learning (ML), these systems have been significantly augmented to fa…
View article: Heterogeneous Privacy Level-Based Client Selection for Hybrid Federated and Centralized Learning in Mobile Edge Computing
Heterogeneous Privacy Level-Based Client Selection for Hybrid Federated and Centralized Learning in Mobile Edge Computing Open
To alleviate the substantial local training burden on clients in the federated learning (FL) process, this paper proposes a more efficient approach based on hybrid federated and centralized learning (HFCL), leveraging the Mobile Edge Compu…
View article: Deep Reinforcement Learning Driven Joint Dynamic TDD and RRC Connection Management Scheme in Massive IoT Networks
Deep Reinforcement Learning Driven Joint Dynamic TDD and RRC Connection Management Scheme in Massive IoT Networks Open
To support dramatically increasing services from internet of thing (IoT) devices with the sporadic and fluctuated generation of short packet traffic, this paper investigates joint dynamic time division duplexing (TDD) and radio resource co…
View article: Energy-Efficient Hybrid Federated and Centralized Learning for Edge-Based Wireless Traffic Prediction in Aerial Networks
Energy-Efficient Hybrid Federated and Centralized Learning for Edge-Based Wireless Traffic Prediction in Aerial Networks Open
This paper designs a novel energy-efficient hybrid federated and centralized learning (HFCL) framework for training wireless traffic prediction models in aerial networks over distributed multi-access edge computing (MEC) servers where mult…
View article: DRL-Enabled Hierarchical Federated Learning Optimization for Data Heterogeneity Management in Multi-Access Edge Computing
DRL-Enabled Hierarchical Federated Learning Optimization for Data Heterogeneity Management in Multi-Access Edge Computing Open
This paper designs a novel Hierarchical Federated Learning (HFL) management scheme, enabled by deep reinforcement learning (DRL), for multi-access edge computing (MEC) environments to accelerate convergence. To do this, the proposed scheme…
View article: Real-Time Dynamic Pricing for Edge Computing Services: A Market Perspective
Real-Time Dynamic Pricing for Edge Computing Services: A Market Perspective Open
Edge computing has emerged as a crucial technology for addressing the increasing demand for low-latency and high-speed services in the era of 5G and beyond. However, efficient resource allocation and pricing in edge computing environments …
View article: Exploring the Privacy-Energy Consumption Tradeoff for Split Federated Learning
Exploring the Privacy-Energy Consumption Tradeoff for Split Federated Learning Open
Split Federated Learning (SFL) has recently emerged as a promising distributed learning technology, leveraging the strengths of both federated and split learning. It emphasizes the advantages of rapid convergence while addressing privacy c…
View article: Leveraging Large Language Models to Generate Answer Set Programs
Leveraging Large Language Models to Generate Answer Set Programs Open
Large language models (LLMs), such as GPT-3 and GPT-4, have demonstrated exceptional performance in various natural language processing tasks and have shown the ability to solve certain reasoning problems. However, their reasoning capabili…
View article: A novel group management scheme of clustered federated learning for mobile traffic prediction in mobile edge computing systems
A novel group management scheme of clustered federated learning for mobile traffic prediction in mobile edge computing systems Open
This study developed a novel group management scheme based on clustered federated learning (FL) for mobile traffic prediction (referred to as FedGM) in mobile edge computing (MEC) systems. In FedGM, to improve the convergence time during t…
View article: Leveraging Large Language Models to Generate Answer Set Programs
Leveraging Large Language Models to Generate Answer Set Programs Open
Large language models (LLMs), such as GPT-3 and GPT-4, have demonstrated exceptional performance in various natural language processing tasks and have shown the ability to solve certain reasoning problems. However, their reasoning capabili…
View article: Coupling Large Language Models with Logic Programming for Robust and General Reasoning from Text
Coupling Large Language Models with Logic Programming for Robust and General Reasoning from Text Open
While large language models (LLMs), such as GPT-3, appear to be robust and general, their reasoning ability is not at a level to compete with the best models trained for specific natural language reasoning problems. In this study, we obser…
View article: Safe Formulas in the General Theory of Stable Models
Safe Formulas in the General Theory of Stable Models Open
Safe first-order formulas generalize the concept of a safe rule, which plays an important role in the design of answer set solvers. We show that any safe sentence is equivalent, in a certain sense, to the result of its grounding -- to the …
View article: Intuitive Access to Smartphone Settings Using Relevance Model Trained by Contrastive Learning
Intuitive Access to Smartphone Settings Using Relevance Model Trained by Contrastive Learning Open
The more new features that are being added to smartphones, the harder it becomes for users to find them. This is because the feature names are usually short, and there are just too many to remember. In such a case, the users may want to as…
View article: NeurASP: Embracing Neural Networks into Answer Set Programming
NeurASP: Embracing Neural Networks into Answer Set Programming Open
We present NeurASP, a simple extension of answer set programs by embracing neural networks. By treating the neural network output as the probability distribution over atomic facts in answer set programs, NeurASP provides a simple and effec…
View article: Learning to Solve Constraint Satisfaction Problems with Recurrent Transformer
Learning to Solve Constraint Satisfaction Problems with Recurrent Transformer Open
Constraint satisfaction problems (CSPs) are about finding values of variables that satisfy the given constraints. We show that Transformer extended with recurrence is a viable approach to learning to solve CSPs in an end-to-end manner, hav…
View article: Injecting Logical Constraints into Neural Networks via Straight-Through Estimators
Injecting Logical Constraints into Neural Networks via Straight-Through Estimators Open
Injecting discrete logical constraints into neural network learning is one of the main challenges in neuro-symbolic AI. We find that a straight-through-estimator, a method introduced to train binary neural networks, could effectively be ap…
View article: Intuitive Access to Smartphone Settings Using Relevance Model Trained by Contrastive Learning
Intuitive Access to Smartphone Settings Using Relevance Model Trained by Contrastive Learning Open
The more new features that are being added to smartphones, the harder it becomes for users to find them. This is because the feature names are usually short and there are just too many of them for the users to remember the exact words. The…
View article: Cognitive Video Surveillance Management in Hierarchical Edge Computing System with Long Short-Term Memory Model
Cognitive Video Surveillance Management in Hierarchical Edge Computing System with Long Short-Term Memory Model Open
Nowadays, deep learning (DL)-based video surveillance services are widely used in smart cities because of their ability to accurately identify and track objects, such as vehicles and pedestrians, in real time. This allows a more efficient …