PALL learns tasks in a single network as sparse subnetworks and performs exact task unlearning by resetting the task's trained parameters and briefly retraining shared ones from a rehearsal buffer.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Privacy-Aware Lifelong Learning
PALL learns tasks in a single network as sparse subnetworks and performs exact task unlearning by resetting the task's trained parameters and briefly retraining shared ones from a rehearsal buffer.