5 papers
BicKD: Bilateral Contrastive Knowledge Distillation
Jiangnan Zhu, Yukai Xu, Li Xiong +4
Knowledge distillation (KD) is a machine learning framework that transfers knowledge from a teacher model to a student model. The vanilla KD proposed by Hinton et al. has been the…
FedSGT: Exact Federated Unlearning via Sequential Group-based Training
Bokang Zhang, Hong Guan, Hong kyu Lee +3
Federated Learning (FL) enables collaborative, privacy-preserving model training, but supporting the "Right to be Forgotten" is especially challenging because data influences the m…
Direct Token Optimization: A Self-contained Approach to Large Language Model Unlearning
Hong kyu Lee, Ruixuan Liu, Li Xiong
Machine unlearning is an emerging technique that removes the influence of a subset of training data (forget set) from a model without full retraining, with applications including p…
Sharpness-Aware Parameter Selection for Machine Unlearning
Saber Malekmohammadi, Hong kyu Lee, Li Xiong
It often happens that some sensitive personal information, such as credit card numbers or passwords, are mistakenly incorporated in the training of machine learning models and need…
Node-level Contrastive Unlearning on Graph Neural Networks
Hong kyu Lee, Qiuchen Zhang, Carl Yang +1
Graph unlearning aims to remove a subset of graph entities (i.e. nodes and edges) from a graph neural network (GNN) trained on the graph. Unlike machine unlearning for models train…