Haekyu Park (박해규)

Ph.D. Student in Computer Science at Georgia Tech
Advisor: Dr. Polo Chau
haekyu@gatech.eduCurriculum VitaeGoogle Scholar
Research Interests
  • Interpretability of Deep Learning / Machine Learning
  • Information / Data Visualization

News


Last updated: Sep 21, 2019

Education


Georgia Institute of Technology

Ph.D., Computer Science
Advisor: Dr. Polo Chau
Aug 2018 - Present




Seoul National University

B.S., Computer Science and Engineering
Graduated with honors (Cum Laude)
Mar 2012 - Aug 2017

Research Experience

Graduate Research Assistant

  • Georgia Institute of Technology, Atlanta, GA

Aug 2018 - Present
Data Science Intern

  • NVIDIA, Austin, TX
  • Mentor: Bartley Richardson, Brad Rees, Joe Eaton
  • The work was integrated into NVIDIA tutorial session at KDD 2019.

May 2019 - Aug 2019
Undergraduate Research Assiatant

  • Seoul National University, Seoul, Republic of Korea

June 2016 - Aug 2017

Publication

2019

Conference [3]
Summit: Scaling Deep Learning Interpretability by Visualizing Activation and Attribution Summarizations
Fred Hohman, Haekyu Park, Caleb Robinson, and Duen Horng Chau
IEEE VIS (VAST), 2019, Vancouver, BC, Canada
[Website] [Demo] [PDF] [arXiv] [BibTeX] [Details]
Other [2]
Visual Analytics for Interpretability on Deep Neural Networks
Haekyu Park, Fred Hohman, Nilaksh Das, Caleb Robinson, and Duen Horng Chau
Women in Machine Learning Workshop (co-located with NeurIPS 2019) (WiML), 2019, Vancouver, BC, Canada
Other [1]
MLsploit: A Cloud-Based Framework for Adversarial Machine Learning Research
Nilaksh Das, Siwei Li, Chanil Jeon, Jinho Jung, Shang-Tse Chen, Carter Yagemann, Evan Downing, Haekyu Park, Evan Yang, Li Chen, Michael Kounavis, Ravi Sahita, David Durham, Scott Buck, Duen Horng Chau, Taesoo Kim, and Wenke Lee
Black Hat Asia - Arsenal, 2019
[Abstract] [Project] [Video]
Poster [1]
NeuralDivergence: Exploring and Understanding Neural Networks by Comparing Activation Distributions
Haekyu Park Fred Hohman, and Duen Horng Chau
IEEE Pacific Visualization Symposium (PacificVis), 2019, Bangkok, Thailand
[PDF] [Website] [arXiv] [BibTeX] [Details]

2018

Conference [2]
SIDE: Representation Learning in Signed Directed Networks
Junghwan Kim, Haekyu Park, Ji-Eun Lee, and U Kang
The Web Conference (Previously known as WWW, World Wide Web Conference) 2018, Lyon, France
[PDF] [Website] [BibTeX] [Details]

2017

Conference [1]
A Comparative Study of Matrix Factorization and Random Walk with Restart in Recommender Systems
Haekyu Park, Jinhong Jung, and U Kang
IEEE International Conference on Big Data (BigData) 2017, Boston, MA, USA
[PDF] [Website] [arXiv] [Slides] [BibTeX] [Details]

Project

2017

Recommender System for Videos on Oksusu Application

  • With SK Telecom, Seoul, Republic of Korea
  • Keywords: Tensorflow, Feedforward Neural Network, Sequence Embedding, Word Embedding, Approx. k-NN
  • [Details]
    We recommend videos to users of Oksusu application. Our model uses deep learning to achieve quality recommendation. Our recommendation engine handles massive data on users' behaviors and heterogeneous information on videos.

Aug - Dec, 2017
A Fast and Cost Efficient Data Compression Algorithm with Shared Virtual Memory in Heterogeneous System Architecture

  • For my undergraduate graduation essay
  • Keywords: OpenCL, GPGPU, SVM, HSA
  • [Details]
    • I used GPGPU and Shared Virtual Memory (SVM) in Heterogeneous System Architecture (HSA).
    • I acquired parallel programming thinking and skills, especially with C++ and OpenCL.
    • We propose fast data deduplication methods that use general purpose computing on graphics processing units (GPGPU) and heterogeneous system architecture (HSA) to efficiently execute the great amount of computations. GPGPU and HSA provide a powerful basis for parallel computing in an easy programmable and efficient way.

Nov 2016 - Aug 2017

2016

Personalized Recommendation for Credit Card Rewards

  • With Hyundai Card, Seoul, Republic of Korea
  • Keywords: Coupled Matrix Factorization, Time Series Data
  • [Details]
    We provide personalized recommendations for credit card rewards to customers. The main algorithm is TCMF (Time Coupled Matrix Factorization). We use various side information of users and items and highly improve the recommendation performance.
  • [News article (in Korean)]

June - Dec, 2016
Social Recommender System with Graph and Rating Information

  • For final project of Probabilistic Graphical Model course
  • Keywords: Matrix Factorization, Network Embedding, Social Network, PGM
  • [Details]
    We designed and implemented a novel recommendation model leveraging social network by network embedding.

Sep - Dec, 2016

Awards & Honors

  • National Scholarship for Science and Engineering
    Merit-based, 2015

Talks & Presentation

  • NeuralDivergence: Exploring and Understanding Neural Networks by Comparing Activation Distributions
    Apr 2019, Poster Presentation, PacificVis

  • A Comparative Study of Matrix Factorization and Random Walk with Restart in Recommender Systems
    Dec 2017, Oral Presentation, IEEE Big Data


Teaching


Technical Skills

  • Programming Languages
    • Python, JavaScript, HTML, R, Matlab, Java, C, C++, Ocaml, Scheme

  • Machine Learning / Deep Learning / Data Science
    • TensorFlow, Keras, scikit-learn, OpenCV, Numpy, Pandas, SciPy, NetworkX

  • GPU-accelerated Data Science
    • cuGraph, cuDF, cuML, BlazingSQL, OpenCL

  • Data Visualization
    • D3.js, HoloViews, Matplotlib, WebGL, ggplot


Professional Service

  • Reviewer
    • KDD 2019


Getting in Touch

I would like to talk to you! Please let me know you more, through
  • Email: haekyu@gatech.edu
  • Address: Coda 1349, Georgia Institute of Technology, 756 W Peachtree St NW, Atlanta, GA 30308