🧿

Publications Details

Research Interests

•

Optimization for training deep neural networks

•

AutoML: automating the tasks of applying machine learning to real-world problems 

•

Trustworthy and real-world AI/ML Challenges 

•

Federated Learning: train an algorithm across multiple decentralized edge devices 

Default view

Publications: Conference and Journal

Title

Conference and Journal

Author

Keyword

Specification

Link

Benchmark Dataset for Precipitation Forecasting by Post-Processing the Numerical Weather Prediction

Open

Arxiv

1st author

Precipitation Nowcasting

Benchmark Dataset

Under Review

https://arxiv.org/abs/2206.15241

Supernet Training for Federated Image Classification under System Heterogeneity

Open

Workshop

ICML2022

1st author

Federated Learning

AutoML

Image Classification

Architecture Search

International

Top-tier

Oral

Under Review

https://arxiv.org/abs/2206.01366

Revisiting Architecture-aware Knowledge Distillation: Smaller Models and Faster Search

Open

Workshop

ICML2022

1st author

Architecture Search

Bayesian Optimization

Knowledge Distillation

Orthogonality Regularization

International

Top-tier

Under Review

https://arxiv.org/abs/2206.13130

Revisiting the Activation Function for Federated Image Classification

Open

Workshop

NeurIPS2022

Co-author

Federated Learning

International

Top-tier

https://openreview.net/forum?id=KGvSg8D5-fY

Revisiting Kernel Orthogonality Regularization: A Study for Convolutional Neural Networks in Image Classification

Open

IEEE Access

1st author

Orthogonality Regularization

International

Journal

https://ieeexplore.ieee.org/document/9804718

Mold into a Graph: Efficient Bayesian Optimization over Mixed-Spaces

Open

Arxiv

Co-author

Hyperparameter Optimization

Graph Neural Network

Working In Progress

https://arxiv.org/abs/2202.00893

Accurate and Fast Federated Learning via Combinatorial Multi-Armed Bandits.

Open

Arxiv

Technical Report

1st author

Federated Learning

Hyperparameter Optimization

Technical Report

https://arxiv.org/abs/2012.03270https://arxiv.org/abs/2012.03270

FINE Samples for Learning with Noisy Labels

Open

NeurIPS2021

1st author

Noisy Label Classification

Image Classification

SVD

International

Top-tier

https://openreview.net/forum?id=QZpx42n0BWr

Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge Distillation

Open

IJCAI2021

1st author

Knowledge Distillation

Noisy Label Classification

Image Classification

International

Top-tier

https://www.ijcai.org/proceedings/2021/0362.pdf

Adaptive Local Bayesian Optimization Over Multiple Discrete Variables

Open

Competition

NeurIPS2020

1st author

AutoML

Hyperparameter Optimization

Bayesian Optimization

Multi-armed Bandit

International

8th rank

https://arxiv.org/abs/2012.03501

Efficient Model for Image Classification With Regularization Tricks

Open

PMLR

Competition

NeurIPS2019

1st author

Orthogonality Regularization

Architecture Search

Augmentation

Model Compression

Image Classification

International

Top-tier

2nd rank

http://proceedings.mlr.press/v123/kim20a

Orthogonal feature regularization : a novel approach for training robust models, Korea Advanced Institute of Science and Technology

Open

Master Thesis

KAIST

1st author

Adversarial Attack

Orthogonality Regularization

Image Classification

Thesis

Region-Conditioned Orthogonal 3D U-Net for Weather4Cast Competition

Open

Competition

NeurIPS2022

1st author

Precipitation Nowcasting

Segmentation

International

Top-tier

4th rank

https://arxiv.org/abs/2212.02059

Layover Intermediate Layer for Multi-Label Classification in Efficient Transfer Learning

Open

Workshop

NeurIPS2022

Co-author

Multi-Label Classification

Efficient

Transfer Learning

International

Top-tier

https://openreview.net/forum?id=mbOHmKLxBH