SPARE: Self-distillation for PARameter-Efficient Removal

1. 1Identify the data or concepts to be removed from the trained model
2. 2Apply self-distillation to retain unrelated concepts and forget specific data
3. 3Evaluate the performance of the model after unlearning to ensure overall performance is preserved
4. 4Fine-tune the model as needed to balance effective forgetting with retention of unrelated concepts

Machine learning engineers and AI researchers on a team can benefit from SPARE to improve model performance and compliance with data protection regulations, while product managers can utilize this technique to develop more responsible AI practices

💡 Self-distillation can be used to efficiently remove the influence of specific data or concepts from trained text-to-image diffusion models

💡 SPARE: Self-distillation for parameter-efficient removal in machine unlearning