一种面向持续学习的遗忘框架
An Unlearning Framework for Continual Learning
AI总结：
针对持续学习中的安全与隐私需求，本文提出无需数据的遗忘框架UnCLe，通过超网络和任务嵌入生成参数并与噪声对齐实现遗忘，在多个视觉数据集上验证了其能在最小干扰下顺序执行学习与遗忘。
摘要：
围绕人工智能安全与数据隐私日益增长的担忧推动了机器遗忘（Machine Unlearning）作为潜在解决方案的发展。然而，当前的机器遗忘算法是为补充离线训练范式而设计的。持续学习（Continual Learning，CL）范式的出现承诺实现增量式模型更新，使模型能够顺序地学习新任务。自然地，其中一些任务可能需要被遗忘，以应对可能出现的隐私或安全关切。我们发现，在持续学习环境中应用传统遗忘算法会产生两个关键问题：保留任务上的性能下降，以及任务复发——即先前被遗忘的任务在后续学习过程中重新出现。此外，大多数遗忘算法需要数据才能运行，这与持续学习丢弃过往数据的理念相冲突。因此，迫切需要一种无需数据且兼顾未来学习的遗忘算法。为此，我们提出了UnCLe，一个面向持续学习的遗忘框架。UnCLe采用一个超网络，利用任务嵌入学习生成任务特定的网络参数。通过将对应生成的网络参数与噪声对齐来实现任务遗忘，无需任何数据。在多个视觉数据集上的实证评估表明，UnCLe能够顺序执行多次学习和遗忘操作，同时对先前已获得知识的干扰最小。
英文摘要：
Growing concerns surrounding AI safety and data privacy have driven the development of Machine Unlearning as a potential solution. However, current machine unlearning algorithms are designed to complement the offline training paradigm. The emergence of the Continual Learning (CL) paradigm promises incremental model updates, enabling models to learn new tasks sequentially. Naturally, some of those tasks may need to be unlearned to address safety or privacy concerns that might arise. We find that applying conventional unlearning algorithms in continual learning environments creates two critical problems: performance degradation on retained tasks and task relapse, where previously unlearned tasks resurface during subsequent learning. Furthermore, most unlearning algorithms require data to operate, which conflicts with CL's philosophy of discarding past data. A clear need arises for unlearning algorithms that are data-free and mindful of future learning. To that end, we propose UnCLe, an Unlearning framework for Continual Learning. UnCLe employs a hypernetwork that learns to generate task-specific network parameters, using task embeddings. Tasks are unlearned by aligning the corresponding generated network parameters with noise, without requiring any data. Empirical evaluations on several vision data sets demonstrate UnCLe's ability to sequentially perform multiple learning and unlearning operations with minimal disruption to previously acquired knowledge.
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。
