no code implementations • 7 Feb 2024 • Ikhyun Cho, Changyeon Park, Julia Hockenmaier
Machine unlearning (MUL) is an arising field in machine learning that seeks to erase the learned information of specific training data points from a trained model.
no code implementations • 17 Jan 2024 • Yoonhwa Jung, Ikhyun Cho, Shun-Hsiang Hsu, Julia Hockenmaier
With growing concerns surrounding privacy and regulatory compliance, the concept of machine unlearning has gained prominence, aiming to selectively forget or erase specific learned information from a trained model.
no code implementations • 28 Nov 2022 • Jaeho Choi, Yura Kim, Kwang-Ho Kim, Sung-Hwa Jung, Ikhyun Cho
PCT-CycleGAN generates temporal causality using two generator networks with forward and backward temporal dynamics in paired complementary cycles.
no code implementations • 30 Sep 2020 • Ikhyun Cho, U Kang
PTP is a KD-specialized initialization method, which can act as a good initial guide for the student.
no code implementations • 28 Sep 2020 • Ikhyun Cho, U Kang
SPS is a new parameter sharing method that allows greater model complexity for the student model.