Machine learning models based on neural networks (NNs) are enjoying ever-increasing attention in the DB community. However, an important issue has been largely overlooked, namely the challenge of dealing with the highly dynamic nature of DBs, where data updates are fundamental, highly-frequent operations. Although some recent research has addressed the issues of maintaining updated NN models in the presence of new data insertions, the effects of data deletions (a.k.a., "machine unlearning") remain a blind spot. With this work, for the first time to our knowledge, we pose and answer the following key questions: What is the effect of unlearning algorithms on NN-based DB models? How do these effects translate to effects on downstream DB tasks, such as selectivity estimation (SE), approximate query processing (AQP), data generation (DG), and upstream tasks like data classification (DC)? What metrics should we use to assess the impact and efficacy of unlearning algorithms in learned DBs? Is the problem of machine unlearning in DBs different from that of machine learning in DBs in the face of data insertions? Is the problem of machine unlearning for DBs different from unlearning in the ML literature? what are the overhead and efficiency of unlearning algorithms? What is the sensitivity of unlearning on batching delete operations? If we have a suitable unlearning algorithm, can we combine it with an algorithm handling data insertions en route to solving the general adaptability/updatability requirement in learned DBs in the face of both data inserts and deletes? We answer these questions using a comprehensive set of experiments, various unlearning algorithms, a variety of downstream DB tasks, and an upstream task (DC), each with different NNs, and using a variety of metrics on a variety of real datasets, making this also a first key step towards a benchmark for learned DB unlearning.

翻译：基于神经网络（NNs）的机器学习模型在数据库领域日益受到关注。然而，一个关键问题长期被忽视，即数据库高度动态性的挑战——数据更新作为基础且高频的操作在其中至关重要。尽管近期研究已涉及新数据插入时更新神经网络模型的问题，但数据删除（即"机器遗忘"）的影响仍是学术盲区。本研究首次提出并解答了以下核心问题：遗忘算法对基于神经网络的数据库模型有何影响？这种影响如何传递至选择性估计、近似查询处理、数据生成等下游数据库任务以及数据分类等上游任务？应使用哪些指标评估学习型数据库中遗忘算法的影响与有效性？数据库中的机器遗忘问题与数据插入场景下的数据库机器学习问题有何差异？数据库中的机器遗忘问题与机器学习文献中的遗忘问题有何不同？遗忘算法的开销与效率如何？遗忘机制对批量删除操作的敏感性如何？若存在合适的遗忘算法，能否将其与处理数据插入的算法结合，以应对学习型数据库中数据插入与删除场景下的通用适应性/可更新性需求？我们通过系统性实验设计，涵盖多种遗忘算法、不同神经网络架构、多个下游数据库任务及一个上游任务（数据分类），采用多维度指标在多个真实数据集上进行验证，这标志着向学习型数据库遗忘基准迈出了关键第一步。