As some recent information security legislation endowed users with unconditional rights to be forgotten by any trained machine learning model, personalized IoT service providers have to put unlearning functionality into their consideration. The most straightforward method to unlearn users' contribution is to retrain the model from the initial state, which is not realistic in high throughput applications with frequent unlearning requests. Though some machine unlearning frameworks have been proposed to speed up the retraining process, they fail to match decentralized learning scenarios. In this paper, we design a decentralized unlearning framework called HDUS, which uses distilled seed models to construct erasable ensembles for all clients. Moreover, the framework is compatible with heterogeneous on-device models, representing stronger scalability in real-world applications. Extensive experiments on three real-world datasets show that our HDUS achieves state-of-the-art performance.

翻译：随着近期部分信息安全法规赋予用户对任何已训练机器学习模型的无条件“被遗忘权”，个性化物联网服务提供商不得不将遗忘功能纳入考量。最直接的遗忘用户贡献的方法是重新从初始状态训练模型，但在高频遗忘请求的高吞吐场景中，这一方法并不现实。尽管已有部分机器遗忘框架被提出以加速重新训练过程，但它们无法适配去中心化学习场景。在本文中，我们设计了一个名为HDUS的去中心化遗忘框架，该框架利用蒸馏得到的种子模型为所有客户端构建可擦除集成。此外，该框架兼容异构的端侧设备模型，在实际应用中展现出更强的可扩展性。在三个真实数据集上的大量实验表明，我们的HDUS取得了最先进的性能。