Forgetting-free Continual Learning with Winning Subnetworks

ICML 2022 Forgetting-free Continual Learning with Winning Subnetworks Haeyong Kang, Rusty Mina, Sultan Rizky Hikmawan Madjid, Jaehong Yoon, Mark Hasegawa-Johnson, Sung Ju Hwang, Chang Yoo    Inspired by Lottery Ticket Hypothesis that competitive subnetworks exist within a de...

Bitwidth Heterogeneous Federated Learning with Progressive Weight Dequantization

ICML 2022 Bitwidth Heterogeneous Federated Learning with Progressive Weight Dequantization Jaehong Yoon, Geon Park, Wonyong Jeong, Sung Ju Hwang    In practical federated learning scenarios, the participating devices may have different bitwidths for computation and memory st...

Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation

ICML 2021 Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation Dongchan Min, Dong Bok Lee, Eunho Yang and Sung Ju Hwang  With rapid progress in neural text-to-speech (TTS) models, personalized speech generation is now in high demand for many applications. For pract...

Learning to Generate Noise for Multi-Attack Robustness

ICML 2021 Learning to Generate Noise for Multi-Attack Robustness Divyam Madaan, Jinwoo Shin and Sung Ju Hwang  Adversarial learning has emerged as one of the successful techniques to circumvent the susceptibility of existing methods against adversarial perturbations. However, the...

Large-Scale Meta-Learning with Continual Trajectory Shifting

ICML 2021 Large-Scale Meta-Learning with Continual Trajectory Shifting JaeWoong Shin, Hae Beom Lee, Boqing Gong and Sung Ju Hwang  Meta-learning of shared initialization parameters has shown to be highly effective in solving few-shot learning tasks. However, extending the framewo...

Federated Continual Learning with Weighted Inter-client Transfer

ICML 2021 Federated Continual Learning with Weighted Inter-client Transfer  Jaehong Yoon, Wonyong Jeong, Giwoong Lee, Eunho Yang, Sung Ju Hwang  There has been a surge of interest in continual learning and federated learning, both of which are important in deep neural n...

Event Prediction Model Considering Time and Input Error Using Electronic Medical Records in the Intensive Care Unit: Retrospective Study

ICML 2021 Event Prediction Model Considering Time and Input Error Using Electronic Medical Records in the Intensive Care Unit: Retrospective Study MinDong Sung, Sangchul Hahn, Chang Hoon Han, Jung Mo Lee, Jayoung Lee, Jinkyu Yoo, Jay Heo, Young Sam Kim, Kyung Soo Chung  In the er...

Adversarial Purification with Score-based Generative Models

ICML 2021 Adversarial Purification with Score-based Generative Models Jongmin Yoon, Sung Ju Hwang and Juho Lee  While adversarial training is considered as a standard defense method against adversarial attacks for image classifiers, adversarial purification, which purifies attack...

Self-supervised Label Augmentation via Input Transformations

ICML 2020 Self-supervised Label Augmentation via Input Transformations Hankook Lee, Sung Ju Hwang, Jinwoo Shin  Self-supervised learning, which learns by constructing artificial labels given only the input signals, has recently gained considerable attention for learning repr...

Federated Continual Learning with Weighted Inter-client Transfer

ICML 2020 workshop in Lifelong Learning Federated Continual Learning with Weighted Inter-client Transfer Jaehong Yoon, Wonyong Jeong, Giwoong Lee, Eunho Yang, Sung Ju Hwang  There has been a surge of interest in continual learning and federated learning, both of which are importa...