Fast-NTK: Parameter-Efficient Unlearning for Large-Scale Models
This work addresses the practical need for scalable data removal in large-scale models to comply with privacy regulations like the Right to be Forgotten, representing an incremental improvement over existing NTK methods.
The paper tackles the computational inefficiency of NTK-based machine unlearning for large models by introducing Fast-NTK, which uses parameter-efficient fine-tuning to scale to networks with 88M parameters and 5k images while maintaining performance similar to retraining.
The rapid growth of machine learning has spurred legislative initiatives such as ``the Right to be Forgotten,'' allowing users to request data removal. In response, ``machine unlearning'' proposes the selective removal of unwanted data without the need for retraining from scratch. While the Neural-Tangent-Kernel-based (NTK-based) unlearning method excels in performance, it suffers from significant computational complexity, especially for large-scale models and datasets. Our work introduces ``Fast-NTK,'' a novel NTK-based unlearning algorithm that significantly reduces the computational complexity by incorporating parameter-efficient fine-tuning methods, such as fine-tuning batch normalization layers in a CNN or visual prompts in a vision transformer. Our experimental results demonstrate scalability to much larger neural networks and datasets (e.g., 88M parameters; 5k images), surpassing the limitations of previous full-model NTK-based approaches designed for smaller cases (e.g., 8M parameters; 500 images). Notably, our approach maintains a performance comparable to the traditional method of retraining on the retain set alone. Fast-NTK can thus enable for practical and scalable NTK-based unlearning in deep neural networks.