About

I am currently an assistant professor in the Division of AI Software Convergence at Dongguk University (DGU), Seoul, South Korea, since March 2021. I received my Ph.D. in Electrical Engineering from Korea Advanced Institute of Science and Technology (KAIST), South Korea, in 2017, under the supervision of Prof. Yung Yi and Prof. Jinwoo Shin. I received my M.S. and B.S. in EE from KAIST in 2012 and 2010, respectively. Prior to joining Dongguk University, I was a research associate in the Department of Informatics at King's College London (KCL), United Kingdom, working with Prof. Osvaldo Simeone. At DGU, I lead the ION research group (Intelligence and Optimization in Networks). 

Research 

My recent research interests lie in mathematical modeling and analysis of communication systems, with a specific focus on applying learning, inference, and control of probabilistic graphical models to communication systems. More generally, the research area covered by my recent and future works is Networked Machine Learning, which takes inspiration from the human brain to carry out supervised, unsupervised, and reinforcement learning tasks in large-scale communication networks. My past research works include network economics, game theory, and distributed algorithms in communication networks. Here are a few examples of my recent/past research topics.

• Learning for Brain-inspired Computing - learning algorithms for dynamic exponential family models [ICASSP2019], for probabilistic Spiking Neural Networks [SPM2019, ICPR2020, ICASSP2021, DSLW2021, NeurIPS2021, COMML2021], and for resource-efficient federated learning [ICASSP2020]

• Learning and Inference of Graphical Models (with applications to large-scale networks) - algorithms for communication efficient structure learning [TNET2022, MOBIHOC2018], for sampling efficient reinforcement learning [IJCAI2019], for fast adaptable parameter learning [TSP2021, SPAWC2019], and for multi time-scale parameter learning [ISIT2017]

• Optimal and Distributed Parameter Control in Graphical Models - optimal CSMA [INFOCOM2014, TWC2018], coordination maximization [MOBIHOC2016, TCNS2019]

• Game Theory and Economics: Networked Market - network economics, pricing of ISPs [JSAC2017, SDP2013]

Education

• Ph.D: Electrical Engineering, KAIST, South Korea, 2012.3~2017.2  (under supervision of Prof. Yung Yi and Prof. Jinwoo Shin)

• M.S: Electrical Engineering, KAIST, South Korea, 2010.3~2012.2  (under supervision of Prof. Yung Yi)

• B.S: Electrical Engineering, KAIST, South Korea, 2006.3~2010.2

Work Experiences

• 2021.03~Present: Assistant Professor, Department of Artificial Intelligence, Dongguk University, South Korea

• 2018.03~2021.02: Research Associate, Centre for Telecommunications Research, Department of Engineering, King's College London, London, England, United Kingdom (Host: Prof. Osvaldo Simeone)

• 2017.03~2018.02: Post-doctoral Researcher, BrainKorea21 Plus, Information & Electronics Research Institute, KAIST, South Korea (Host: Prof. Yung Yi)

• 2015.06~2015.10: Research Intern, Center of Non-Linear Studies, Los Alamos National Laboratory, NM, United States (Host: Dr. Michael Chertkov)

Honors and Awards

• Audience Choice Paper Award, IEEE Data Science & Learning Workshop (DSLW), 2021

• BK21 Plus Scholarship, South Korea, 2017

• Qualcomm Innovation Award, Qualcomm, 2016

• National Scholarship, South Korea, 2006~2016

Project Experiences

• 2021.06~2024.02: Research on Resource-Efficient Federated Learning for On-Device Intelligence, National Research Foundation of Korea (한국연구재단), South Korea

• 2021.07~2023.12: Development of Standards for 5G-Advanced Network Intelligence and Automation based on Machine Learning, IITP, South Korea (Lead PI: 한국전자통신연구원) 

• 2021.03~Present: High Performance Knowledge System 개발 및 인력양성, 대학ICT연구센터(ITRC), South Korea 

• 2018.04~2021.02: Intel's Neuromorphic Research Community (INRC), Intel

  • Attend workshops with leading researchers in the fields of neuroscience-inspired Artificial Intelligence and neuromorphic computing 

• 2018.04~2021.02: FOG-aided wireless networks for communication, cacHing and cOmputing: theoRetical and algorithmic fouNdations (FOGHORN), European Research Council (ERC)

  • Develop fundamental theoretical insights, via network information theory, communication theory and machine learning, on the optimal performance and operation of fog-aided wireless networks 

• 2017.07~2018.03: Research on Learning-based Service Improvement Framework in Large-scale Online Request System, Naver, South Korea

  • Design and analyze Reinforcement Learning based service improvement framework in large-scale online request system

  • Implement deep reinforcement learning algorithm for service improvement in large-scale online request system 

• 2014.10~2015.06: Bosch-KAIST Smart Car Project: Look Ahead: Shared Sensing for Cooperative Cars, Bosch, German - Korea

  • Design and implement MAC protocol for real-time video transmission between vehicles

• 2013.11~2016.10: Research on Horizontal and Vertical Decoupling in Big Wireless Networks: Theory and Implementation, National Research Foundation of Korea (NRF) grant funded by the Ministry of Science, ICT & Future Planning (MSIP), South Korea

  • Research on distributed MAC protocol design for CSMA-based wireless networks (from optimization and game theory perspective)

• 2011.06~2011.10: Research on Smart Network based B2B2C Service Modeling and Economic Analysis, Korea Telecom, South Korea

  • Research on analysis of economic value of pricing between Internet Service Providers, Content Providers, and users

Presentation Experiences

• "BiSNN: Training Spiking Neural Networks with Binary Weights via Bayesian Learning", at IEEE Data Science and Learning Workshop (DSLW), Virtual Conference, June 2021. 

• "Multi-Sample Online Learning for Spiking Neural Networks based on Generalized Expectation Maximization", at IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Virtual Conference, June 2021. 

• "VOWEL: A Local Online Learning Rule for Recurrent Networks of Probabilistic Spiking Winner-Take-All Circuits", at International Conference on Pattern Recognition (ICPR), Virtual Conference, January 2021. 

• "Training Dynamic Exponential Family Models with Causal and Lateral Dependencies for Generalized Neuromorphic Computing", at IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Brighton, UK, May 2019. [poster]

• "Information-Theoretic Learning of Probabilistic Spiking Neural Networks", at INRC Workshop, Reykjavik, Iceland, September 2018. [poster] 

• "Learning Data Dependency with Communication Cost," at ACM Mobile Ad Hoc Networking and Computing (MOBIHOC), Los Angeles, USA, June 27, 2018. [slide]

• "Adiabatic Persistent Contrastive Divergence Learning", at IEEE International Symposium on Information Theory (ISIT), Aachen, Germany, June 30, 2017. [slide] 

• "Optimization and Learning of Graphical Models: A Stochastic Approximation Approach", at Korea Computer Congress (KCC): Spotlight Session for Young Women Scholars, Jeju, South Korea, June 20, 2017. [slide] 

• "Distributed Coordination Maximization over Networks: A Stochastic Approximation Approach", at ACM Mobile Ad Hoc Networking and Computing (MobiHoc), Paderborn, Germany, July 7, 2016. [slide] 

• "Distributed Learning for Utility Maximization over CSMA-based Wireless Multihop Networks", at IEEE International Conference on Computer Communications (INFOCOM), Toronto, Canada, April 29, 2014. [slide] 

• "On the Interaction between ISP Revenue Sharing and Network Neutrality", at ACM International Conference on emerging Networking Experiments and Technologies (CoNEXT) Student workshop, Philadelphia, USA, November 30, 2010. [poster] 

Teaching Experiences

• Instructor, Programming for Machine Learning (AIX6031), DGU, Spring 2021

• Instructor, Python Programming for Data Science (DSC4001), DGU, Spring 2021

• Teaching Assistant, Communication Systems (6CCS3COS), KCL, Fall 2018

• Teaching Assistant, Optimization in Communication Networks (EE650), KAIST, Spring 2016, Spring 2013

• Teaching Assistant, Programming Structures for Electrical Engineering (EE209), KAIST, Fall 2014

• Teaching Assistant, Computer Networks (EE323), KAIST, Spring 2014, Spring 2011

• Teaching Assistant, Data Structure and Algorithms for Electrical Engineering (EE205), KAIST, Fall 2013, Fall 2011

• Teaching Assistant, Economics in Communication Networks (EE655), KAIST, Spring 2012

Reference Available on Request

• Professor Yung Yi: Professor at the School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), South Korea, yiyung at kaist dot edu, +82 (0) 42 350 3486

• Professor Jinwoo Shin: Associate Professor at the Graduate School of AI & School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), South Korea, jinwoos at kaist dot ac dot kr

• Professor Osvaldo Simeone: Professor at the Department of Engineering, King's College London (KCL), United Kingdom, osvaldo dot simeone at kcl dot ac dot uk

• Professor Se-Young Yun: Assistant Professor at the Graduate School of AI & Department of Industrial and Systems Engineering, Korea Advanced Institute of Science and Technology (KAIST), South Korea, yunseyoung at kaist dot ac dot kr