Woojeong Jin

Computer Science Researcher

Hello! I am a researcher in Data Mining Lab. at Seoul National University, where I am advised by Professor U Kang.

My research interest lies in large-scale data mining and machine learning, especially for social networks and the Web with a focus on developing computational frameworks and designing novel and scalable algorithms for analyzing large-scale datasets.

Email: woojeong.jin (at) gmail.com
[Curriculum Vitae]


Supervised and Extended Restart in Random Walks for Ranking and Link Prediction in Networks
Woojeong Jin, Jinhong Jung, and U Kang
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD - journal track) 2018, Dublin, Ireland. (under review)
[ paper | www (code and data) | arXiv ]
Relation Inference using Labeled Random Walk with Restart in Edge-labeled Graphs
Jinhong Jung, Woojeong Jin, and U Kang
Thirty-fifth International Conference on Machine Learning (ICML) 2018 (under review)
[ paper | supplement ]
Fast and Accurate Random Walk with Restart on Dynamic Graphs with Guarantees
Minji Yoon, Woojeong Jin, and U Kang
The Web Conference (WWW) 2018, Lyon, France (to appear)
[ paper | arXiv | bib ] (14.8% Acceptance Rate)
Ranking in Signed Social Networks: Model and Algorithms
Jinhong Jung, Woojeong Jin, U Kang, and Lee Sael
Knowledge and Information Systems (KAIS) (under revision)
[ paper | www (code and data) ]
Personalized Ranking in Signed Networks using Signed Random Walk with Restart
Jinhong Jung, Woojeong Jin, Lee Sael, and U Kang
IEEE International Conference on Data Mining (ICDM) 2016, Barcelona, Spain
[ paper | supplement | www (code and data) | bib ] (19.6% Acceptance Rate)
Recommender System based on Graph Ranking using Random Walk
Woojeong Jin, Jinhong Jung, and U Kang
Communications of the Korean Institute of Information Scientists and Engineers (KIISE), 2016
[ paper ]


Method for Providing Supervised and Extended Restart in Random Walks for Ranking and Link Prediction in Networks, KR: 10-2017-0131543 (filed on Nov. 10, 2017)
Woojeong Jin, Jinhong Jung, and U Kang

Method for Personalized Ranking in Signed Networks, Recording Medium And Device for Performing the Method, KR: 10-2017-0005485 (filed on Jan. 12, 2017)
Jinhong Jung, Woojeong Jin, and U Kang


May 2016 - Present

Building Energy Optimization Technology based on Deep Learning and IoT

with Samsung Electronics Co., Ltd.

  • Developed IoT sensor kits using Arduino Board.
  • Developed multi-input CNN for real-time recognition of room occupancy and activity.
  • Developed 3D CNN for sequential sensor data.
  • Developed RNN for room occupancy and activity prediction

Work Experience

Jan. 2016 - Present


Data Mining Lab., SNU

  • Advisor: Prof. U Kang
  • Proposed a novel algorithm for random walk with restart on signed networks. (ICDM'16, KAIS)
  • Proposed a dynamic RWR algorithm on dynamic graphs. (WWW'18)
  • Propose an extended RWR algorithm and a supervised learning algorithm for link prediction. (ongoing)
  • Propose a labeled RWR algorithm on edge-labeled graphs. (ongoing)
  • Design a local clustering algorithm in signed networks. (ongoing)
  • Participate in developing algorithms for activity recognition and prediction for HVAC control. (ongoing)
Jan. 2015 - June 2015

Undergraduate Researcher

Data Science Lab., SNU

  • Advisor: Prof. Sungroh Yoon
  • Worked on comparisons between deep learning frameworks (Caffe, Cuda-convnet, and Theano) using Convolutional Neural Networks.
June 2014 - Aug. 2014

Research Intern

Creative Innovation Center, LG electronics

  • Assisted in developing the prototype of advanced smartphones.
  • Tested application of a flexible display to smartphones.

Relevant Coursework

Pattern Recognition and Machine Learning (Audit), SNU, Spring 2017
Convex Optimization, SNU, Fall 2016
Mining Massive Datasets, Stanford Online, June 2017
Machine Learning (Stanford University), Coursera, May 2016


Mar. 2010 - Feb. 2017

B.S. in Electrical and Computer Engineering

Seoul National University

Seoul, Korea