methodology-7
Continual Forgetting
3260 papers • 126 benchmarks • 313 datasets
Selective information is expected to be continuously removed from a pre-trained model while maintaining the rest.
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in continual-forgetting-14
Trend
Dataset
Best Model
Actions
No benchmarks available.
Libraries
iUse these libraries to find continual-forgetting-14 models and implementations
Datasets
No datasets available.
Subtasks
No subtasks available.
Most implemented papers
Continual Forgetting for Pre-Trained Vision Models
Yuntao Chen, Hongbo Zhao, Bolin Ni, Haochen Wang, Junsong Fan, Fei Zhu, Yuxi Wang, Gaofeng Meng, Zhaoxiang Zhang•Sun Mar 17 2024
Group Sparse LoRA is effective, parameter-efficient, data-efficient, data-efficient, and easy to implement, and it is demonstrated that GS-LoRA manages to forget specific classes with minimal impact on other classes.
23