paper-with-me

Papers

A More Practical Approach to Machine Unlearning

2024-06-13 · David Zagardo

Machine learning models often incorporate vast amounts of data, raising significant privacy concerns. Machine unlearning, the ability to remove the influence of specific data points from a trained model, addresses these concerns. This paper explores practical methods for implementing machine unlearning, focusing on a first-epoch gradient-ascent approach. Key findings include: 1. Single vs. Multi-Epoch Unlearning: First-epoch gradient unlearning is more effective than multi-epoch gradients. 2. Layer-Based Unlearning: The embedding layer in GPT-2 is crucial for effective unlearning. Gradients from the output layers (11 and 12) have no impact. Efficient unlearning can be achieved using only the embedding layer, halving space complexity. 3. Influence Functions & Scoring: Techniques like Hessian Vector Product and the dot product of activations and tensors are used for quantifying unlearning. 4. Gradient Ascent Considerations: Calibration is necessary to avoid overexposing the model to specific data points during unlearning, which could prematurely terminate the process. 5. Fuzzy Matching vs. Iterative Unlearning: Fuzzy matching techniques shift the model to a new optimum, while iterative unlearning provides a more complete modality. Our empirical evaluation confirms that first-epoch gradient ascent for machine unlearning is more effective than whole-model gradient ascent. These results highlight the potential of machine unlearning for enhancing data privacy and compliance with regulations such as GDPR and CCPA. The study underscores the importance of formal methods to comprehensively evaluate the unlearning process.

📄 PDF Abstract BibTeX arXiv:2406.09391

Code (0)

등록된 구현이 없습니다.

Tasks

Machine Unlearning

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Adam 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Weight Decay 설명 없음

Similar Papers 제목 키워드 기반

Auditing Machine Unlearning: A Systematic Research on Whether Models Truly Forget

2026-06-15 · Dayong Ye, Tianqing Zhu, Ruiding Huang, Xinbo Fu 외 arxiv

Machine unlearning has been extensively studied in response to growing privacy concerns and regulatory requirements. However, auditing whether unlearning algorithms have truly erased the influence of specific data remain…

Unlearning with Control: Assessing Real-world Utility for Large Language Model Unlearning

2024-06-13 · Qizhou Wang, Bo Han, Puning Yang, Jianing Zhu 외

The compelling goal of eradicating undesirable data behaviors, while preserving usual model functioning, underscores the significance of machine unlearning within the domain of large language models (LLMs). Recent resear…

Language ModelingLanguage ModellingLarge Language ModelMachine Unlearning

Releasing Malevolence from Benevolence: The Menace of Benign Data on Machine Unlearning

2024-07-06 · Binhao Ma, Tianhang Zheng, Hongsheng Hu, Di Wang 외

Machine learning models trained on vast amounts of real or synthetic data often achieve outstanding predictive performance across various domains. However, this utility comes with increasing concerns about privacy, as th…

Data PoisoningMachine Unlearning

Efficient Knowledge Deletion from Trained Models through Layer-wise Partial Machine Unlearning

2024-03-12 · Vinay Chakravarthi Gogineni, Esmaeil S. Nadimi

Machine unlearning has garnered significant attention due to its ability to selectively erase knowledge obtained from specific training data samples in an already trained machine learning model. This capability enables d…

Machine Unlearning

Towards Natural Machine Unlearning

2024-05-24 · Zhengbao He, Tao Li, Xinwen Cheng, Zhehao Huang 외

Machine unlearning (MU) aims to eliminate information that has been learned from specific training data, namely forgetting data, from a pre-trained model. Currently, the mainstream of existing MU methods involves modifyi…

Machine Unlearning