SISA++ uses weight averaging of shard-trained models to outperform SISA in retaining SER and DD performance after user-data unlearning on CREMA-D and E-DAIC.
cookbook recipes
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Towards Machine Unlearning for Paralinguistic Speech Processing
SISA++ uses weight averaging of shard-trained models to outperform SISA in retaining SER and DD performance after user-data unlearning on CREMA-D and E-DAIC.