2 papers
cs.LG2025
Sparse Tuning Enhances Plasticity in PTM-based Continual Learning
Huan Zhang, Shenghua Fan, Shuyu Dong +3
Continual Learning with Pre-trained Models holds great promise for efficient adaptation across sequential tasks. However, most existing approaches freeze PTMs and rely on auxiliary…
cs.LG2024
Constructing Enhanced Mutual Information for Online Class-Incremental Learning
Huan Zhang, Fan Lyu, Shenghua Fan +2
Online Class-Incremental continual Learning (OCIL) addresses the challenge of continuously learning from a single-channel data stream, adapting to new tasks while mitigating catast…