Unlearning is challenging in generic learning frameworks with the continuous growth and updates of models exhibiting complex inheritance relationships. This paper presents a novel unlearning framework that enables fully parallel unlearning among models exhibiting inheritance. We use a chronologically Directed Acyclic Graph (DAG) to capture various unlearning scenarios occurring in model inheritance networks. Central to our framework is the Fisher Inheritance Unlearning (FIUn) method, designed to enable efficient parallel unlearning within the DAG. FIUn utilizes the Fisher Information Matrix (FIM) to assess the significance of model parameters for unlearning tasks and adjusts them accordingly. To handle multiple unlearning requests simultaneously, we propose the Merging-FIM (MFIM) function, which consolidates FIMs from multiple upstream models into a unified matrix. This design supports all unlearning scenarios captured by the DAG, enabling one-shot removal of inherited knowledge while significantly reducing computational overhead. Experiments confirm the effectiveness of our unlearning framework. For single-class tasks, it achieves complete unlearning with 0% accuracy for unlearned labels while maintaining 94.53% accuracy for retained labels. For multi-class tasks, the accuracy is 1.07% for unlearned labels and 84.77% for retained labels. Our framework accelerates unlearning by 99% compared to alternative methods. Code is in https://github.com/MJLee00/Parallel-Unlearning-in-Inherited-Model-Networks.

翻译：在模型持续增长与更新且呈现复杂继承关系的通用学习框架中，遗忘学习具有挑战性。本文提出了一种新颖的遗忘学习框架，能够在具有继承关系的模型间实现完全并行遗忘。我们使用时序有向无环图（DAG）来捕捉模型继承网络中出现的各种遗忘场景。框架的核心是费舍尔继承遗忘（FIUn）方法，旨在实现DAG内的高效并行遗忘。FIUn利用费舍尔信息矩阵（FIM）评估模型参数对遗忘任务的重要性，并相应调整参数。为同时处理多个遗忘请求，我们提出合并FIM（MFIM）函数，将来自多个上游模型的FIM整合为统一矩阵。该设计支持DAG涵盖的所有遗忘场景，实现继承知识的一次性移除，同时显著降低计算开销。实验验证了本遗忘学习框架的有效性。在单类别任务中，对于遗忘标签实现了0%准确率的完全遗忘，同时保留标签的准确率保持在94.53%。在多类别任务中，遗忘标签的准确率为1.07%，保留标签的准确率为84.77%。与替代方法相比，本框架将遗忘学习速度提升了99%。代码位于https://github.com/MJLee00/Parallel-Unlearning-in-Inherited-Model-Networks。