Efficient Continual Learning and On-Device Training for Mobile and IoT Devices
Young D. Kwon
University of Cambridge Ph.D. Thesis, September 2024
| PDF
| BibTex
| Link
Geographical engagement and churn prediction in location-based social networks
Young D. Kwon
HKUST M.Phil. Thesis, January 2020
| PDF
| BibTex
| Link
Speculative Decoding with a Speculative Vocabulary
Miles Williams, Young D. Kwon, Rui Li,
Alexandros Kouris, and Stylianos I. Venieris
arXiv 2026
| PDF
| Link
Tempora: Characterising the Time-Contingent Utility of Online Test-Time Adaptation
Sudarshan Sreeram, Young D. Kwon, and
Cecilia Mascolo
arXiv 2026
| PDF
| Link
Efficient High-Resolution Image Editing with Hallucination-Aware Loss and Adaptive Tiling
Young D. Kwon, Abhinav Mehrotra, Malcolm
Chadwick, Albert Gil Ramos, and Sourav Bhattacharya
arXiv 2025
| PDF
| Link
On-demand Test-time Adaptation for Edge Devices
Xiao MA, Young D. Kwon, and Dong MA
arXiv 2025
| PDF
| Link
MetaCLBench: Meta Continual Learning Benchmark on Resource-Constrained Edge Devices
Young D. Kwon*, Sijia Li*, Lik-Hang Lee,
and Pan Hui
arXiv 2025
| PDF
| Link
| * Co-first authors
LeanTTA: A Backpropagation-Free and Stateless Approach to Quantized Test-Time Adaptation on Edge Devices
Cynthia Dong, Hong Jia, Young D. Kwon,
Georgios Rizos, and Cecilia Mascolo
arXiv 2025
| PDF
| Link
HideNseek: Federated Lottery Ticket via Server-side Pruning and Sign Supermask
Anish K. Vallapuram, Pengyuan Zhou, Young D. Kwon
, Lik Hang Lee, Hengwei Xu, and Pan Hui
arXiv 2022
| PDF
| Link
Architecture-Agnostic Test-Time Adaptation via Backprop-Free Embedding Alignment
Xiao Ma, Young D. Kwon, Pan Zhou, and Dong
Ma
ICLR 2026
| PDF
| BibTex
| Link
| Code
HierarchicalPrune: Position-Aware Compression for Large-Scale Diffusion Models
Young D. Kwon*, Rui Li*, Sijia Li, Da Li,
Sourav Bhattacharya, and Stylianos Venieris
AAAI 2026
| PDF
| Poster
| Slides
| BibTex
| Link
| * Co-first authors
TinyTrain: Resource-Aware Task-Adaptive Sparse Training of DNNs at the Data-Scarce Edge
Young D. Kwon, Rui Li, Stylianos I.
Venieris, Jagmohan Chauhan, Nicholas D. Lane, and Cecilia Mascolo
ICML 2024
| PDF
| Poster
| Slides
| BibTex
| Link
TinyTTA: Efficient Test-time Adaptation via Early-exit Ensembles on Edge Devices
Hong Jia, Young D. Kwon, Alessio Orsino,
Ting Dang, Domenico Talia, and Cecilia Mascolo
NeurIPS 2024
| PDF
| Poster
| Slides
| BibTex
| Link
| Code
A Framework for On-Device Uncertainty-Aware Event Detection on Microcontrollers
Hong Jia, Young D. Kwon, Dong Ma, Nhat
Pham, Lorena Qendro, Tam Vu, and Cecilia Mascolo
PMCJ 2024
UR2M: Uncertainty and Resource-Aware Event Detection on Microcontrollers
Hong Jia, Young D. Kwon, Dong Ma, Nhat
Pham, Lorena Qendro, Tam Vu, and Cecilia Mascolo
PerCom 2024
| PDF
| BibTex
LifeLearner: Hardware-Aware Meta Continual Learning System for Embedded Computing Platforms
Young D. Kwon, Jagmohan Chauhan, Hong Jia,
Stylianos I. Venieris, and Cecilia Mascolo
SenSys 2023
| PDF
| BibTex
ChatGPT in education: A blessing or a curse? A qualitative study exploring early adopters’ utilization and perceptions
Reza Hadi Mogavi, Chao Deng, Justin Juho Kim, Pengyuan Zhou, Young D. Kwon
, Ahmed Hosny Saleh Metwally, Ahmed Tlili, Simone Bassanelli, Antonio Bucchiarone, Sujit Gujar,
Lennart E. Nacke, and Pan Hui
Computers in Human Behavior: Artificial Humans 2023
| PDF
| BibTex
| Link
YONO: Modeling Multiple Heterogeneous Neural Networks on Microcontrollers
Young D. Kwon, Jagmohan Chauhan, and
Cecilia Mascolo
IPSN 2022
| PDF
| BibTex
| Link
PROS: an Efficient Pattern-Driven Compressive Sensing Framework for Low-Power Biopotential-based Wearables with On-chip Intelligence
Nhat Pham, Hong Jia, Minh Tran, Tuan Dinh, Nam Bui, Young D. Kwon
, Dong Ma, VP Nguyen, Cecilia Mascolo, Tam Vu
MobiCom 2022
| PDF
| BibTex
| Link
Exploring On-Device Learning Using Few Shots for Audio Classification
Jagmohan Chauhan, Young D. Kwon, and
Cecilia Mascolo
EUSIPCO 2022
| PDF
| BibTex
| Link
MyoKey: Inertial Motion Sensing and Gesture-based QWERTY Keyboard for Extended Realities
Kirill A. Shatilov, Young D. Kwon,
Lik-Hang Lee, Dimitris Chatzopoulos, and Pan Hui
TMC 2022
| PDF
| BibTex
| Link
Causal Analysis on the Anchor Store Effect in a Location-based Social Network
Anish Krishna Vallapuram, Young D. Kwon,
Lik-Hang Lee, Fengli Xu, Pan Hui
ASONAM 2022
| PDF
| BibTex
| Link
Enabling On-Device Smartphone GPU based Training: Lessons Learned
Anish Das, Young D. Kwon, Jagmohan
Chauhan, and Cecilia Mascolo
PerFail (PerCom 2022 Workshop)
| PDF
| BibTex
| Link
Exploring System Performance of Continual Learning for Mobile and Embedded Sensing Applications
Young D. Kwon, Jagmohan Chauhan, Abhishek
Kumar, Pan Hui, and Cecilia Mascolo
SEC 2021
| PDF
| BibTex
| Link
Interpretable Business Survival Prediction
Anish Krishna Vallapuram, Nikhil Nanda, Young D. Kwon
, and Pan Hui
ASONAM 2021
| PDF
| BibTex
| Link
IAN: Interpretable Attention Network for Churn Prediction in LBSNs
Liang-Yu Chen, Yutong Chen, Young D. Kwon,
Youwen Kang, and Pan Hui
ASONAM 2021
| PDF
| BibTex
| Link
FastICARL: Fast Incremental Classifier and Representation Learning with Efficient Budget Allocation in Audio Sensing Applications
Young D. Kwon, Jagmohan Chauhan, and
Cecilia Mascolo
Interspeech 2021
| PDF
| BibTex
| Link
Knowing when we do not know: Bayesian continual learning for sensing-based analysis tasks
Sandra Servia Rodriguez, Cecilia Mascolo, and Young D. Kwon
arXiv
| PDF
| BibTex
| Link
ContAuth: Continual Learning Framework for Behavioral-based User Authentication
Jagmohan Chauhan, Young D. Kwon, Pan Hui,
and Cecilia Mascolo
IMWUT/UbiComp 2021
| PDF
| BibTex
| Link
Aquilis: Using Contextual Integrity for Privacy Protection on Mobile Devices
Abhishek Kumar, Tristan Braud, Young D. Kwon
, and Pan Hui
IMWUT/UbiComp 2021
| PDF
| BibTex
| Link
Enemy at the Gate: Evolution of Twitter User's Polarization During National Crisis
Ehsan Ul Haq, Tristan Braud, Young D. Kwon
, and Pan Hui
ASONAM 2020
| PDF
| BibTex
A Survey on Computational Politics
Ehsan Ul Haq, Tristan Braud, Young D. Kwon
, and Pan Hui.
IEEE Access
| PDF
| BibTex
| Link
MyoKey: Surface Electromyography and Inertial Motion Sensing-based Text Entry in AR
Young D. Kwon, Kirill A. Shatilov,
Lik-Hang Lee, Serkan Kumyol, Kit Yung Lam, Yui-Pan Yau, and Pan Hui
PerCom 2020 WIP
| PDF
| Slides
| BibTex
| Link
GeoLifecycle: User Engagement of Geographical Exploration and Churn Prediction in LBSNs
Young D. Kwon, Dimitris Chatzopoulos,
Ehsan Ul Haq, Raymond Chi-Wing Wong, and Pan Hui.
IMWUT/UbiComp 2019
| PDF
| Slides
| BibTex
| Link
Effects of Ego Networks and Communities on Self-Disclosure in an Online Social Network
Young D. Kwon, Reza Hadi Mogavi, Ehsan Ul
Haq, Youngjin Kwon, Xiaojuan Ma, and Pan Hui
ASONAM 2019
| PDF
| Slides
| BibTex
| Link
UbiComp/ISWC 2019: A Post-Conference Summary Report
Young D. Kwon, Mohammed Khwaja, Neille-Ann
H. Tan, Marla Narazani, Mikolaj P. Wozniak, Arshad Nasser, Rahul Majethia, Lucy Van Kleunen,
Victoria Neumann, and Rajkarn Singh
IEEE Pervasive Computing, 2019 (Impact Factor: 3.813)
| PDF
| BibTex
| Link
Document Summarization Considering Entailment Relation between Sentences
Youngdae Kwon, Noo-ri Kim, and Jee-Hyong
Lee
Journal of KIISE: Software and Application 2017
| Link
Document Summarization Considering Entailment Relation between Sentences
Youngdae Kwon, Noo-ri Kim, and Jee-Hyong
Lee
Proceedings of the KIISE conference 2016
| Link
Method to Discover Novel Attribute Relationships using Social-Attribute Network in Google+
Youngdae Kwon, Chung Kwan Tse, Chong Bor
Hung, and Cheuk Man Chiu
Proceedings of the KIISE conference 2015
| Link
Efficient Continual Learning and On-Device Training for Mobile and IoT Devices
Young D. Kwon
University of Cambridge Ph.D. Third Year Report, Sep 2023
| PDF
| BibTex
On-Device Training at the Extreme Edge
Young D. Kwon
SenSys '23 Ph.D. Forum, Nov 2023
| PDF
| BibTex
Efficient Continual and On-device Learning in Mobile Computing
Young D. Kwon
University of Cambridge Ph.D. Second Year Report, Jun 2022
| PDF
| BibTex
Efficient Meta Continual Learning on the Edge
Young D. Kwon
SEC '21 Ph.D. Forum, Dec 2021
| PDF
| BibTex
Efficient On-device Systems that can Sense, Learn, and Optimize Continually in the Wild
Young D. Kwon
University of Cambridge Ph.D. First Year Report, June 2021
| PDF
| BibTex
Optimising DNN Processing on Extremely
Resource-Limited Devices
Research Intern (Advisor: Dr. Stylianos I. Venieris, Dr. Rui Li, and Prof. Nicholas D. Lane
) · Apr. 2022 ~ Apr. 2023
• Participated in various projects related to optimising DNN processing on extremely
resource-constrained devices
Incremental Learning on
Resource-constrained Devices
Research Assistant (Advisor:
Dr. Jagmohan Chauhan and Prof. Cecilia Mascolo
) · Jul. 2020 ~ Sep. 2020
• Participated in a project to apply incremental learning on resource-constrained devices
A Study of Applying Neural Networks on a
Database
Research Assistant (Advisor:
Prof. Dimitris Papadias
) · Feb. 2020 ~ Jun. 2020
• Participated in a project to apply neural networks on a database
Computer Laboratory at the University of
Cambridge
Visiting Research Student (Advisor:
Dr. Jagmohan Chauhan and Prof. Cecilia Mascolo
) · Jul. 2019 ~ Dec. 2019
• Investigated the Catastrophic Forgetting problem on mobile systems
User Engagement Analysis and Churn
Prediction with LBSN Datasets
Postgraduate Research Student (Advisor:
Prof. Raymond Wong
and Prof. Pan Hui) · Aug. 2018 ~ May. 2019
• Conducted a quantitative analysis to understand user engagement patterns exhibited both offline
and online in LBSNs
• Examined the behavioral differences between churners and stayers among highly active users from
various aspects; significantly improved the performance of churn prediction task over all baselines
using our proposed features
• Paper accepted in the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
(IMWUT/UbiComp), 2019 as the first author
• Investigated a project of characterizing users and predicting potential long-term contributors in
LBSNs
HKUST-DT System and Media Laboratory at
HKUST
Postgraduate Research Student (Advisor: Prof. Pan Hui) · Aug. 2017 ~ Jan. 2020
• Carried out my own project on users' self-disclosing behaviors in online social networks. The
resulting paper was accepted in ASONAM 2019 as the first author
• Participated in a project of Ph.D. student
Ehsan Ul Haq on inferring political leaning of users in a Q&A forum
• Involved in a project of Ph.D. student Reza Hadi Mogavi on predicting churning users in a Q&A forum
Information & Intelligence System Lab. at SKKU
Research Intern (Advisor: Prof. Jee-Hyong Lee) · Sep. 2015 - June. 2016
• Proposed a new algorithm, TextRank-NLI, which combines a Deep Learning based Natural Language
Inference model and a Graph-based ranking algorithm used in a single document extraction-based
summarization task
Social Network Analysis Project with Social-Attribute Network
Dataset of Google+
Undergraduate Research Student (Advisor: Prof. Pan Hui) · Feb. 2015 ~ June. 2015
• Researched to discover novel relationships using association rule mining with attributes of users
in Google+ social-attribute networks