2025
Hybrid Re-matching for Continual Learning with Parameter-Efficient Tuning
This work proposes HRM-PET, which makes full use of the richer downstream knowledge inherently contained in the trained parameters, and introduces a hybrid re-matching mechanism, which benefits from the initial predicted distribution to facilitate the parameter selections.
Weicheng Wang, Guoli Jia, Xialei Liu et al.
· Neural Information Processin... · 0 citations