arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2410.23232cs.LG
收藏

Attribute-to-Delete:基于Datamodel Matching的机器遗忘

Attribute-to-Delete: Machine Unlearning via Datamodel Matching

MIT(麻省理工学院);Harvard Business School(哈佛商学院);Harvard SEAS(哈佛大学工程与应用科学学院);Stanford(斯坦福大学);Microsoft Research(微软研究院);Stanford Statistics(斯坦福大学统计系)

Kristian Georgiev, Roy Rinberg, Sung Min Park, Shivam Garg, Andrew Ilyas, Aleksander Madry, Seth Neel

AI总结:

本研究提出了一种名为Datamodel Matching(DMM)的机器遗忘元算法,通过将遗忘问题归约为数据归因问题,在非凸环境中实现了优于现有算法的遗忘性能,并为未来研究指明了方向。

摘要:

机器遗忘——即高效地移除一小部分“遗忘集”训练数据对预训练机器学习模型的影响——近期引起了广泛的研究兴趣。然而,尽管有这种兴趣,最近的研究表明,现有的机器遗忘技术在非凸环境下的全面评估中表现不佳。在本研究中,我们引入了一种新的机器遗忘技术,即使在这种具有挑战性的环境中也能展现出强大的经验性能。我们的出发点是这样的观点:遗忘的目标是生成一个模型,其输出在统计上与在除遗忘集之外的所有数据上重新训练的模型输出无法区分。这一观点自然地暗示了从遗忘问题到数据归因问题的归约,后者的目标是预测改变训练集对模型输出的影响。受此启发,我们提出了以下元算法,我们称之为Datamodel Matching(DMM):给定一个训练好的模型,我们(a)使用数据归因来预测如果模型在除遗忘集数据点之外的所有数据上重新训练时的输出;然后(b)微调预训练模型以匹配这些预测输出。在一个简单的凸环境中,我们展示了该方法如何可证明地优于多种迭代遗忘算法。在经验上,我们结合现有评估和基于KL散度的新指标,表明即使在非凸环境中,DMM相对于现有算法也实现了强大的遗忘性能。DMM的一个额外好处是它是一个元算法,即数据归因方面的未来进展可直接转化为更好的遗忘算法,为遗忘领域的未来进展指明了明确方向。

英文摘要:

Machine unlearning -- efficiently removing the effect of a small "forget set" of training data on a pre-trained machine learning model -- has recently attracted significant research interest. Despite this interest, however, recent work shows that existing machine unlearning techniques do not hold up to thorough evaluation in non-convex settings. In this work, we introduce a new machine unlearning technique that exhibits strong empirical performance even in such challenging settings. Our starting point is the perspective that the goal of unlearning is to produce a model whose outputs are statistically indistinguishable from those of a model re-trained on all but the forget set. This perspective naturally suggests a reduction from the unlearning problem to that of data attribution, where the goal is to predict the effect of changing the training set on a model's outputs. Thus motivated, we propose the following meta-algorithm, which we call Datamodel Matching (DMM): given a trained model, we (a) use data attribution to predict the output of the model if it were re-trained on all but the forget set points; then (b) fine-tune the pre-trained model to match these predicted outputs. In a simple convex setting, we show how this approach provably outperforms a variety of iterative unlearning algorithms. Empirically, we use a combination of existing evaluations and a new metric based on the KL-divergence to show that even in non-convex settings, DMM achieves strong unlearning performance relative to existing algorithms. An added benefit of DMM is that it is a meta-algorithm, in the sense that future advances in data attribution translate directly into better unlearning algorithms, pointing to a clear direction for future progress in unlearning.

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。

↑