Machine Unlearning, the process of selectively eliminating the influence of certain data examples used during a model's training, has gained significant attention as a means for practitioners to comply with recent data protection regulations. However, existing unlearning methods face critical drawbacks, including their prohibitively high cost, often associated with a large number of hyperparameters, and the limitation of forgetting only relatively small data portions. This often makes retraining the model from scratch a quicker and more effective solution. In this study, we introduce Gradient-based and Task-Agnostic machine Unlearning ($\nabla \tau$), an optimization framework designed to remove the influence of a subset of training data efficiently. It applies adaptive gradient ascent to the data to be forgotten while using standard gradient descent for the remaining data. $\nabla \tau$ offers multiple benefits over existing approaches. It enables the unlearning of large sections of the training dataset (up to 30%). It is versatile, supporting various unlearning tasks (such as subset forgetting or class removal) and applicable across different domains (images, text, etc.). Importantly, $\nabla \tau$ requires no hyperparameter adjustments, making it a more appealing option than retraining the model from scratch. We evaluate our framework's effectiveness using a set of well-established Membership Inference Attack metrics, demonstrating up to 10% enhancements in performance compared to state-of-the-art methods without compromising the original model's accuracy.

翻译：机器反学习是一种选择性消除模型训练过程中特定数据样本影响的技术，作为实践者遵守最新数据保护法规的手段，已引起广泛关注。然而，现有反学习方法存在关键缺陷，包括通常与大量超参数相关的高昂成本，以及仅能遗忘较小数据比例的限制。这往往使从头重新训练模型成为更快捷有效的解决方案。在本研究中，我们提出基于梯度且任务无关的机器反学习（$\nabla \tau$），这是一种旨在高效消除训练数据子集影响的优化框架。它对需遗忘数据应用自适应梯度上升，同时对剩余数据使用标准梯度下降。$\nabla \tau$ 相较于现有方法具有多项优势。它能够遗忘训练数据集中的大部分数据（高达30%）。该方法通用性强，支持多种反学习任务（如子集遗忘或类别移除），并可应用于不同领域（图像、文本等）。尤为重要的是，$\nabla \tau$ 无需调整超参数，使其成为比从头重新训练模型更具吸引力的选择。我们使用一系列成熟的成员推理攻击指标评估框架有效性，结果表明，与最先进方法相比，其性能提升高达10%，且未影响原始模型的准确性。