MaxDiv: Zero-Shot Machine Unlearning via Distributionally Divergent Erasing Samples
Bibliographic record
Abstract
For the sake of data privacy, erasing some knowledge that was acquired during the original training emerges as a pivotal necessity, which is called machine unlearning. Particularly, when the model does not have access to the original training data, such unlearning is even more difficult. In this paper, we address the challenging problem of zero-shot machine unlearning by introducing an innovative approach, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MaxDiv</i>, which generates specially crafted erasing samples. These samples are strategically generated by negating the distributions of the data to be forgotten. We also integrate knowledge distillation techniques into MaxDiv in order to prevent the catastrophic forgetting about the information to be retained. Through extensive empirical evaluations conducted on MNIST, SVHN, CIFAR-10, CIFAR-100, and TinyImageNet datasets, our proposed zero-shot unlearning paradigm showcases superior performance compared to the current state-of-the-art methods.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.003 |
| Science and technology studies | 0.003 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; both teacher heads agree on what is shown here.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".