面向对齐数据遗忘的双机机器学习
Towards Aligned Data Forgetting via Twin Machine Unlearning
AI总结：
针对机器遗忘中数据遗忘与黄金模型对齐的目标，提出双机机器学习方法，通过孪生问题训练预测器迁移，显著提升遗忘模型与黄金模型的对齐程度。
摘要：
现代隐私法规推动了机器遗忘技术的发展，该技术使训练模型能够高效地遗忘特定训练数据。在以往的遗忘方法中，“数据遗忘”的概念常被解释并实现为在该数据上达到零分类准确率。然而，机器遗忘的真正目标是实现遗忘模型与黄金模型之间的对齐，即鼓励它们具有相同的分类准确率。另一方面，黄金模型由于其泛化能力，往往表现出非零的分类准确率。为了实现对齐的数据遗忘，我们提出了一种双机机器学习（Twin Machine Unlearning, TMU）方法，其中针对原始遗忘问题定义了一个孪生遗忘问题。因此，在孪生问题上训练得到的泛化标签预测器可以迁移到原始问题，从而促进对齐的数据遗忘。全面的实证实验表明，我们的方法显著增强了遗忘模型与黄金模型之间的对齐程度。
英文摘要：
Modern privacy regulations have spurred the evolution of machine unlearning, a technique enabling a trained model to efficiently forget specific training data. In prior unlearning methods, the concept of "data forgetting" is often interpreted and implemented as achieving zero classification accuracy on such data. Nevertheless, the authentic aim of machine unlearning is to achieve alignment between the unlearned model and the gold model, i.e., encouraging them to have identical classification accuracy. On the other hand, the gold model often exhibits non-zero classification accuracy due to its generalization ability. To achieve aligned data forgetting, we propose a Twin Machine Unlearning (TMU) approach, where a twin unlearning problem is defined corresponding to the original unlearning problem. Consequently, the generalization-label predictor trained on the twin problem can be transferred to the original problem, facilitating aligned data forgetting. Comprehensive empirical experiments illustrate that our approach significantly enhances the alignment between the unlearned model and the gold model.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
