边缘遗忘并非“处于边缘”！一种在资源受限设备上的自适应精确遗忘系统
Edge Unlearning is Not "on Edge"! An Adaptive Exact Unlearning System on Resource-Constrained Devices
AI总结：
提出网络边缘的约束感知自适应精确遗忘系统（CAUSE），通过基于Fibonacci的替换策略、自适应分片和模型剪枝，在资源受限设备上以极低开销实现精确遗忘，在速度、能耗和精度上显著优于现有系统。
摘要：
“被遗忘权”要求机器学习模型能够擦除数据所有者的数据及信息。仅从数据集中删除数据是不够的，因为模型会记忆训练数据中的信息，从而增加用户的潜在隐私风险。为解决此问题，已开发并部署了多种机器遗忘技术。其中，近似遗忘是一种流行方案，但近期研究表明其遗忘效果无法得到完全保证。另一种方法即精确遗忘，通过丢弃数据并从头重新训练模型来解决该问题，但代价是消耗大量的计算和内存资源。然而，并非所有设备都有能力执行此类重训练。在众多机器学习应用中，如边缘设备、物联网、移动设备和卫星，资源受到限制，这为部署现有精确遗忘方法带来了挑战。在本研究中，我们提出了一种网络边缘的约束感知自适应精确遗忘系统（CAUSE），这是一种在资源受限设备上实现精确遗忘的方法。CAUSE旨在通过在资源受限设备上存储子模型来最小化重训练开销，创新性地应用了基于Fibonacci的替换策略，并在基于用户的数据分区过程中自适应地更新分片数量。为进一步提高内存使用效率，CAUSE利用模型剪枝的优势，通过压缩来节省内存，同时仅有极小的精度损失。实验结果表明，在资源受限设备上实现精确遗忘方面，CAUSE在遗忘速度、能耗和精度上分别比其他代表性系统显著提升了9.23%-80.86%、66.21%-83.46%和5.26%-194.13%。
英文摘要：
The right to be forgotten mandates that machine learning models enable the erasure of a data owner's data and information from a trained model. Removing data from the dataset alone is inadequate, as machine learning models can memorize information from the training data, increasing the potential privacy risk to users. To address this, multiple machine unlearning techniques have been developed and deployed. Among them, approximate unlearning is a popular solution, but recent studies report that its unlearning effectiveness is not fully guaranteed. Another approach, exact unlearning, tackles this issue by discarding the data and retraining the model from scratch, but at the cost of considerable computational and memory resources. However, not all devices have the capability to perform such retraining. In numerous machine learning applications, such as edge devices, Internet-of-Things (IoT), mobile devices, and satellites, resources are constrained, posing challenges for deploying existing exact unlearning methods. In this study, we propose a Constraint-aware Adaptive Exact Unlearning System at the network Edge (CAUSE), an approach to enabling exact unlearning on resource-constrained devices. Aiming to minimize the retrain overhead by storing sub-models on the resource-constrained device, CAUSE innovatively applies a Fibonacci-based replacement strategy and updates the number of shards adaptively in the user-based data partition process. To further improve the effectiveness of memory usage, CAUSE leverages the advantage of model pruning to save memory via compression with minimal accuracy sacrifice. The experimental results demonstrate that CAUSE significantly outperforms other representative systems in realizing exact unlearning on the resource-constrained device by 9.23%-80.86%, 66.21%-83.46%, and 5.26%-194.13% in terms of unlearning speed, energy consumption, and accuracy.
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。
