SE2D stabilizes continual distillation across heterogeneous teachers by preserving logits on external unlabeled data to mitigate unseen knowledge forgetting.
Three types of incremental learning.Nature Machine Intelligence, 4(12):1185–1197, 2022
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Continual Distillation of Teachers from Different Domains
SE2D stabilizes continual distillation across heterogeneous teachers by preserving logits on external unlabeled data to mitigate unseen knowledge forgetting.