Breaking the Trilemma of Privacy, Utility, Efficiency via Controllable Machine Unlearning
-
Updated
May 19, 2024 - Python
Breaking the Trilemma of Privacy, Utility, Efficiency via Controllable Machine Unlearning
A framework for machine unlearning.
Code for Large Language Model Unlearning via Embedding-Corrupted Prompts
Code for the paper "DUCK: Distance-based Unlearning via Centroid Kinematics"
An implementation of the SIGMOD24 paper: Machine Unlearning in Learned DBs: An Experimental Analysis
This repo contains data and code for Task-Aware Machine Unlearning with Application to Load Forecasting.
Unlearning Graph Classifiers with Limited Data Resources (TheWebConf 2023)
"Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning" by Chongyu Fan*, Jiancheng Liu*, Alfred Hero, Sijia Liu
Official PyTorch Implementation for Continual Learning and Private Unlearning
An Empirical Study of Federated Unlearning: Efficiency and Effectiveness (Accepted Conference Track Papers at ACML 2023)
A federated clustering approach with the corresponding unlearning mechanism (ICLR 2023)
Certified (approximate) machine unlearning for simplified graph convolutional networks (SGCs) with theoretical guarantees (ICLR 2023)
Machine Unlearning for Random Forests
Code for CVPR22 paper "Deep Unlearning via Randomized Conditionally Independent Hessians"
Continual Forgetting for Pre-trained Vision Models (CVPR 2024)
General Strategy for Unlearning in Graph Neural Networks
Official implementation of "Graph Unlearning" (ACM CCS 2022)
Official implementation of "When Machine Unlearning Jeopardizes Privacy" (ACM CCS 2021)
[NeurIPS23 (Spotlight)] "Model Sparsity Can Simplify Machine Unlearning" by Jinghan Jia*, Jiancheng Liu*, Parikshit Ram, Yuguang Yao, Gaowen Liu, Yang Liu, Pranay Sharma, Sijia Liu
[ICLR24 (Spotlight)] "SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation" by Chongyu Fan*, Jiancheng Liu*, Yihua Zhang, Eric Wong, Dennis Wei, Sijia Liu
Add a description, image, and links to the machine-unlearning topic page so that developers can more easily learn about it.
To associate your repository with the machine-unlearning topic, visit your repo's landing page and select "manage topics."