A LoRA-based residual feature alignment method for efficient machine unlearning on pre-trained models by targeting zero residuals on retained data and shifted residuals on unlearned data.
Learning word vectors for sentiment analysis,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Proposes a framework for collaborative dataset construction and smart-contract-hosted ML models on blockchain, with financial and gamified incentives to sustain accuracy.
citing papers explorer
-
Machine Unlearning on Pre-trained Models by Residual Feature Alignment Using LoRA
A LoRA-based residual feature alignment method for efficient machine unlearning on pre-trained models by targeting zero residuals on retained data and shifted residuals on unlearned data.
-
Decentralized & Collaborative AI on Blockchain
Proposes a framework for collaborative dataset construction and smart-contract-hosted ML models on blockchain, with financial and gamified incentives to sustain accuracy.