4 papers
TOUR: A Trajectory-Level Unlearning Benchmark for Offline Reinforcement Learning
Chaofan Pan, Lingfei Ren, Xiangyu Jiang +6
Offline Reinforcement Learning (RL) agents are trained on fixed behavioral trajectories, which makes trajectory-level deletion important when selected data must be removed after tr…
Improving Open-world Continual Learning under the Constraints of Scarce Labeled Data
Yujie Li, Xiangkun Wang, Xin Yang +3
Open-world continual learning (OWCL) adapts to sequential tasks with open samples, learning knowledge incrementally while preventing forgetting. However, existing OWCL still requir…
ErrorEraser: Unlearning Data Bias for Improved Continual Learning
Xuemei Cao, Hanlin Gu, Xin Yang +4
Continual Learning (CL) primarily aims to retain knowledge to prevent catastrophic forgetting and transfer knowledge to facilitate learning new tasks. Unlike traditional methods, w…
Order-Robust Class Incremental Learning: Graph-Driven Dynamic Similarity Grouping
Guannan Lai, Yujie Li, Xiangkun Wang +3
Class Incremental Learning (CIL) aims to enable models to learn new classes sequentially while retaining knowledge of previous ones. Although current methods have alleviated catast…