Sangwon Seo

Sangwon Seo

Auto-generated profile, based on publicly available information

Sangwon Seo

KTH Royal Institute of Technology

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 December 2021 in IEEE Transactions on Mobile Computing
Verified
Journal Article
Closed access
HKHaneul Ko
Haneul Ko
JLJaewook Lee
Jaewook Lee
SSSangwon Seo
Sangwon Seo
Sangheon PackSangheon Pack
Sangheon Pack
Victor C. M. LeungVictor C. M. Leung
Victor C. M. Leung
In federated learning (FL), if the participating mobile devices have low computing power and poor wireless channel conditions and/or they do not have sufficient data for various classes, a long convergence time is required to achieve the desired model accuracy. To address this problem, we first formulate a constrained Markov decision process (CMDP) problem that aims to minimize the average time of rounds while maintaining the numbers of trained data and trained data classes above certain numbers. To obtain the optimal scheduling policy, the formulated CMDP problem is converted into an equivalent linear programming (LP). Additionally, to overcome the problem of the curse of dimensionality in CMDP, we develop a joint client selection and bandwidth allocation algorithm (J-CSBA) that jointly selects appropriate mobile devices and allocates suitable amount of bandwidth to them at each round by considering their data information, computing power, and channel gain. Evaluation results validate that J-CSBA can reduce the convergence time by up to $49\%$ compared to a conventional random scheme.

9 September 2022 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
JLJaewook Lee
Jaewook Lee
HKHaneul Ko
Haneul Ko
SSSangwon Seo
Sangwon Seo
Sangheon PackSangheon Pack
Sangheon Pack
Federated learning (FL) has received significant attention as a practical alternative to traditional cloud-centric machine learning (ML). The performance (e.g., accuracy and convergence time) of FL is hampered by the selection of clients having non-independent and identically distributed (non-IID) data. In addition, a long convergence time is inevitable if clients with poor computation or communication capabilities participate in the FL procedure (i.e., the straggler problem). To minimize convergence time while guaranteeing high learning accuracy, we first formulate an optimization problem on client selection. As a practical solution, we devise a data distribution-aware online client selection (DOCS) algorithm. In DOCS, the FL server finds several clusters having near IID data and then uses a multi-armed bandit (MAB) technique to select the cluster with the lowest convergence time. The evaluation results demonstrate that DOCS can reduce the convergence time by up to $10\% \sim 41\%$ and improve the learning accuracy by up to $4\% \sim 13\%$ compared to the traditional client selection schemes.

6 December 2023
Verified
Conference Paper
Open access
SMSamie Mostafavi
Samie Mostafavi
VMVishnu Narayanan Moothedath
Vishnu Narayanan Moothedath
SRStefan Ronngren
Stefan Ronngren
NRNeelabhro Roy
Neelabhro Roy
GSGourav Prateek Sharma
Gourav Prateek Sharma
JGJames Gross
James Gross
This paper presents ExPECA, an edge computing and wireless communication research testbed designed to tackle two pressing challenges: comprehensive end-to-end experimentation and high levels of experimental reproducibility. Leveraging OpenStack-based Chameleon Infrastructure (CHI) framework for its proven flexibility and ease of operation, ExPECA is located in a unique, isolated underground facility, providing a highly controlled setting for wireless experiments. The testbed is engineered to facilitate integrated studies of both communication and computation, offering a diverse array of Software-Defined Radios (SDR) and Commercial Off-The-Shelf (COTS) wireless and wired links, as well as containerized computational environments. We exemplify the experimental possibilities of the testbed using OpenRTiST, a latency-sensitive, bandwidth-intensive application, and analyze its performance. Lastly, we highlight an array of research domains and experimental setups that stand to gain from ExPECA's features, including closed-loop applications and time-sensitive networking.

28 March 2023 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
SSSangwon Seo
Sangwon Seo
JLJaewook Lee
Jaewook Lee
HKHaneul Ko
Haneul Ko
Sangheon PackSangheon Pack
Sangheon Pack
In federated learning (FL), which clients and quantization levels are selected for the deep model parameters has a significant impact on learning time as well as learning accuracy. This is not a trivial issue because it is also significantly affected by factors such as computational power, communication capacity, and data distribution. Considering these factors, we formulate a joint optimization problem for clustering and selecting clusters with quantization levels. Due to the high complexity of the formulated problem, we propose a situation-aware cluster and quantization level selection (SITUA-CQ) algorithm. In this algorithm, the FL server first assembles clients into clusters to mitigate the impact of biased data distributions and determines the most suitable clusters and quantization levels based on their computing power and channel quality. Extensive simulation results show that SITUA-CQ can reduce the round time by up to 80.3% compared to conventional algorithms.

9 June 2025 in IEEE Access
Verified
Journal Article
Open access
HKHaneul Ko
Haneul Ko
SSSangwon Seo
Sangwon Seo
Sangheon PackSangheon Pack
Sangheon Pack
Split computing has emerged as a promising approach to alleviate the resource constraints of IoT devices by offloading computation to edge servers. However, conventional split computing schemes fail to effectively support multi-task learning (MTL) models, which feature a shared backbone and multiple task-specific branches. These structural characteristics, combined with the variability of network conditions, require a more flexible and adaptive offloading strategy. In this paper, we propose a deep reinforcement learning (DRL)-based dynamic split computing framework (D2SCF) tailored for the MTL model. In D2SCF, the MTL model is first split into a head model of the shared layers and several tail models for the task-specific layers (i.e., individual output branches). Subsequently, an IoT device makes decisions regarding the split computing of the head and tail models. To minimize the average task completion time across multiple tasks and the energy consumption of the IoT device, we formulate a Markov decision process problem. The formulated problem is solved using a model-free DRL algorithm (i.e., a deep deterministic policy gradient). Evaluation results demonstrate that D2SCF reduces the average task completion time by more than 50% compared to conventional split computing schemes, while maintaining low energy consumption on the IoT device. Moreover, it consistently outperforms baseline methods across heterogeneous network settings, confirming its robustness in dynamic environments.

16 May 2022 in Electronics
Verified
Journal Article
Open access
PDF file
SLSang-Hoon Lee
Sang-Hoon Lee
SSSangwon Seo
Sangwon Seo
Soochang ParkSoochang Park
Soochang Park
TKTae-Sung Kim
Tae-Sung Kim
Along with the recent advance in wireless networking and data processing technologies, demands for low latency communication (LLC) are increasing in a wide variety of future-driven autonomous applications such as a smart factory, self-driving cars, and so on. The fifth generation of cellular mobile communications (5G) will cover this need as one of three key capacities in their usage scenarios: enhanced mobile broadband (eMBB), massive machine type communication (mMTC), and ultra-reliable low-latency communications (URLLC). The 5G systems are composed of mobile devices and various internet of things (IoT) devices for sensing, acting, and information services; they configure diverse networking topologies such as direct mobile-to-mobile, also known as device-to-device (D2D). In the 5G D2D network systems, the network topologies are easily broken because of the mobile devices such as smartphones, IoT devices, and so on. Thus, for the highly flexible and extensible 5G D2D network systems, mobility support for the mobile devices is necessary. In this paper, we first explore the mobility issues in beyond 5G D2D. Since there are static and mobile elements in the 5G application domains such as the smart factory, overall mobility would lead to highly frequent topology reconfiguration or connectivity reconstruction. Thus, latency-related problems derived from topology changes and connectivity failures due to the mobility are addressed. To handle the problems, a fast connectivity construction scheme, denoted by LMK, is proposed with a deep neural network dealing with learning on radio signal information in order to achieve the LLC. Evaluation results demonstrate that the proposed framework can provide reliable connectivity for the MAC layer link with a low latency data transmission.