Mitigate noisy data for smart IoT via GAN based machine unlearning  

作　　者：Zhuo MA Yilong YANG Yang LIU Xinjing LIU Jianfeng MA 

机构地区：[1]School of Cyber Engineering,Xidian University,Xi’an 710071,China [2]State Key Laboratory of Integrated Services Networks(ISN),Xi’an 710071,China

出　　处：《Science China(Information Sciences)》2024年第3期58-74,共17页中国科学（信息科学）（英文版）

基　　金：supported by National Key Research and Development Program of China (Grant No.2022YFB3103500);National Natural Science Foundation of China (Grant Nos.U21A20464,61872283);Natural Science Basic Research Program of Shaanxi (Grant No.2021JC-22);Key Research and Development Program of Shaanxi (Grant No.2022GY029);China 111 Project (Grant No.B16037)。

摘　　要：With the development of IoT applications,machine learning dramatically improves the utility of variable IoT systems such as autonomous driving.Although the pretrain-finetune framework can cope well with data heterogeneity in complex IoT scenarios,the data collected by sensors often contain unexpected noisy data,e.g.,out-of-distribution(OOD)data,which leads to the reduced performance of fine-tuned models.To resolve the problem,this paper proposes Mu GAN,a method that can mitigate the side-effect of OOD data via the generative adversarial network(GAN)-based machine unlearning.Mu GAN follows a straightforward but effective idea to mitigate the performance loss caused by OOD data,i.e.,“flashbacking”the model to the condition where OOD data are excluded from model training.To achieve the goal,we design an adversarial game,where a discriminator is trained to identify whether a sample belongs to the training set by observing the confidence score.Meanwhile,a generator(i.e.,the target model)is updated to fool the discriminator into believing that the OOD data are not included in the training set but others do.The experimental results show that benefiting from the high unlearning rate(more than 90%)and retention rate(99%),Mu GAN succeeds in lowering the model performance degradation caused by OOD data from 5.88%to 0.8%.

关 键 词：machine unlearning generative adversarial network out of distribution data Internet of Thing neural network 

分 类 号：TN929.5[电子电信—通信与信息系统] TP391.44[电子电信—信息与通信工程] TP181[自动化与计算机技术—计算机应用技术]