avatar

Taehyung Kwon

Postdoctoral Researcher
KAIST
taehyung.kwon (at) kaist.ac.kr


About Me

I am a Postdoctoral Researcher at the Information & Electronics Research Institute, KAIST, working with Prof. Kijung Shin. I received a Ph.D. degree in Artificial Intelligence at KAIST in 2026, advised by Prof. Prof. Kijung Shin. I received B.S. in Computer Science from KAIST. My research interests include tensor decomposition, data compression, and data distillation.

Education

KAIST

Publications

  1. [C9] Effective Dataset Distillation for Spatio-Temporal Forecasting with Bi-dimensional Compression (to appear)
    Taehyung Kwon*, Yeonje Choi*, Yeongho Kim, and Kijung Shin
    ICDE 2026
  2. [J3] Effective and Lightweight Lossy Compression of Tensors: Techniques and Applications
    Jihoon Ko, Taehyung Kwon, Jinhong Jung, and Kijung Shin
    Knowledge and Information Systems
    PDF Code&Datasets
  3. [C8] Simple yet Effective Node Property Prediction on Edge Streams under Distribution Shifts
    Jongha Lee, Taehyung Kwon, Heechan Moon, and Kijung Shin
    ICDE 2025
    PDF Code&Datasets
  4. [C7] Kronecker Generative Models for Power-Law Patterns in Real-World Hypergraphs
    Minyoung Choe, Jihoon Ko, Taehyung Kwon, Kijung Shin, and Christos Faloutsos
    WWW 2025
    PDF Code&Datasets
  5. [J2] Begin: Extensive Benchmark Scenarios and an Easy-to-use Framework for Graph Continual Learning
    Jihoon Ko*, Shinhwan Kang*, Taehyung Kwon, Heechan Moon, and Kijung Shin
    ACM TIST: ACM Transactions on Intelligent Systems and Technology
    PDF Code&Datasets
  6. [J1] Compact Lossy Compression of Tensors via Neural Tensor-Train Decomposition
    Taehyung Kwon, Jihoon Ko, Jinhong Jung, Jun-Gi Jang, and Kijung Shin
    Knowledge and Information Systems
    PDF Code&Datasets
  7. [C6] ELiCiT: Effective and Lightweight Lossy Compression of Tensors
    Jihoon Ko, Taehyung Kwon, Jinhong Jung, and Kijung Shin
    ICDM 2024
    PDF Code&Datasets
  8. [C5] Compact Decomposition of Irregular Tensors for Data Compression: From Sparse to Dense to High-Order Tensors
    Taehyung Kwon, Jihoon Ko, Jinhong Jung, Jun-Gi Jang, Kijung Shin
    KDD 2024
    PDF Code&Datasets Slide BibTex
  9. [C4] TensorCodec: Compact Lossy Compression of Tensors without Strong Data Assumptions
    Taehyung Kwon, Jihoon Ko, Jinhong Jung, and Kijung Shin
    ICDM 2023
    Best Student Paper Runner-up Award [Link]
    PDF Code&Datasets Slide BibTex
  10. [C3] NeuKron: Constant-Size Lossy Compression of Sparse Reorderable Matrices and Tensors
    Taehyung Kwon*, Jihoon Ko*, Jinhong Jung, and Kijung Shin
    WWW 2023
    PDF Code&Datasets Slide BibTex
  11. [C2] Finding a Concise, Precise, and Exhaustive Set of Near Bi-Cliques in Dynamic Graphs
    Hyeonjeong Shin, Taehyung Kwon, Neil Shah, and Kijung Shin
    WSDM 2022
    PDF Code&Datasets BibTex
  12. [P1] Learning to Pool in Graph Neural Networks for Extrapolation
    Jihoon Ko, Taehyung Kwon, Kijung Shin, and Juho Lee
    Preprint, 2021.
    PDF BibTex
  13. [C1] SliceNStitch: Continuous CP Decomposition of Sparse Tensor Streams
    Taehyung Kwon*, Inkyu Park*, Dongjin Lee, and Kijung Shin
    ICDE 2021
    PDF Code&Datasets Slide BibTex

Awards and Honors

Professional Service

Conference Reviewers

Journal Reviewers


Powered by Jekyll and Minimal Light theme.