计算机工程2025，Vol.51Issue(12)：56-67,12.DOI:10.19678/j.issn.1000-3428.0070658
一种基于不确定性校正的可信连续学习方法
A Trusted Continuous Learning Method Based on Uncertainty Correction
SHEN Qinfeng 1HUANG Luyao2
作者信息
- 1. School of Cyber Science and Engineering,Southeast University,Nanjing 211189,Jiangsu,China||Jiangyin Huazi Secondary Specialized School,Wuxi 214401,Jiangsu,China
- 2. School of Cyber Science and Engineering,Southeast University,Nanjing 211189,Jiangsu,China
- 折叠
摘要
Abstract
As a deep learning paradigm that can be trained in continuous data streams,continuous learning is suitable for increasingly open and complex intelligent application scenarios.The main challenge in incremental learning is catastrophic forgetting,which refers to a precipitous drop in performance on previously learned tasks after learning a new task.State-of-the-art studies on continuous learning ignore the impact of uncertainty on model training.In addition,existing studies mainly focus on mitigating forgetting in the phases after the initial phase,whereas the role of the initial phase is largely neglected.Motivated by this,this study proposes a trusted continuous learning method based on uncertainty correction that constrains the uncertainty of a model at the initial stage.Thus,this constraint can alleviate errors caused by model parameter drift,and catastrophic forgetting can be relieved.The proposed method can be combined with other continuous learning methods;therefore,it is fairly universal;for example,this study improves three traditional continuous learning models using the proposed method,and the experimental results show that the improved models outperform the original ones,with the Average Classification Accuracy(ACA)improving by 1.2 to 19.1 percentage points on two datasets.The Expected Calibration Error(ECE)is used to evaluate the reliability of the models.The experimental results show that the improved models have a lower ECE,which proves that the proposed method improves the reliability of the original models.关键词
连续学习/不确定性/校正/信息熵/知识蒸馏Key words
continuous learning/uncertainty/correction/information entropy/knowledge distillation分类
信息技术与安全科学引用本文复制引用
SHEN Qinfeng,HUANG Luyao..一种基于不确定性校正的可信连续学习方法[J].计算机工程,2025,51(12):56-67,12.
