arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2511.09414cs.LG
收藏

探测再编辑:面向工业物联网中无保留数据机器遗忘的推拉框架

Probing then Editing: A Push-Pull Framework for Retain-Free Machine Unlearning in Industrial IoT

Jiao Chen, Weihua Li, Jianhua Tang

AI总结:

针对工业物联网中模型遗忘需保留数据的问题,提出无保留数据的探测再编辑(PTE)框架,通过探测决策边界生成编辑指令、推拉协同优化拆解目标类别决策区域并锚定保留类别知识,在多基准上实现遗忘效果与模型效用的优异平衡。

摘要:

在动态工业物联网(IIoT)环境中,模型需要具备选择性遗忘过时或错误知识的能力。然而,现有方法通常依赖保留数据来约束模型行为,这增加了计算和能源负担,且与工业数据孤岛及隐私合规要求相冲突。为此,我们提出一种新型无保留数据遗忘框架,称为探测再编辑(PTE)。PTE将遗忘构建为探测-编辑过程:首先,通过梯度上升探测模型在待遗忘类别上的决策边界邻域,并利用模型自身预测生成相应编辑指令;随后执行推拉协同优化:推分支利用编辑指令主动拆解目标类别的决策区域,拉分支通过掩码知识蒸馏将模型在保留类别上的知识锚定至原始状态。得益于该机制,PTE仅使用待遗忘数据和原始模型即可实现高效且平衡的知识编辑。实验结果表明,在CWRU和SCUT-FD等多个通用及工业基准上,PTE在遗忘效果与模型效用间取得了优异平衡。

英文摘要:

In dynamic Industrial Internet of Things (IIoT) environments, models need the ability to selectively forget outdated or erroneous knowledge. However, existing methods typically rely on retain data to constrain model behavior, which increases computational and energy burdens and conflicts with industrial data silos and privacy compliance requirements. To address this, we propose a novel retain-free unlearning framework, referred to as Probing then Editing (PTE). PTE frames unlearning as a probe-edit process: first, it probes the decision boundary neighborhood of the model on the to-be-forgotten class via gradient ascent and generates corresponding editing instructions using the model's own predictions. Subsequently, a push-pull collaborative optimization is performed: the push branch actively dismantles the decision region of the target class using the editing instructions, while the pull branch applies masked knowledge distillation to anchor the model's knowledge on retained classes to their original states. Benefiting from this mechanism, PTE achieves efficient and balanced knowledge editing using only the to-be-forgotten data and the original model. Experimental results demonstrate that PTE achieves an excellent balance between unlearning effectiveness and model utility across multiple general and industrial benchmarks such as CWRU and SCUT-FD.

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。

↑