基于神经元统计建模分析的模型不确定性度量
Model Uncertainty Measurement Based on Neuron Statistical Modeling and Analysis
雷雅婧1
作者信息
- 1. 复旦大学计算机科学技术学院,上海 200438
- 折叠
摘要
神经网络的不确定性反映模型对自身预测结果的置信水平,能在决策不可靠时促使及时的人工干预,提升系统安全性.然而,现有度量方法常需要对模型或训练过程进行显著修改且实施复杂度高.为此,本文提出一种基于神经元统计建模分析的不确定性度量方法.该方法充分利用模型单次前向传播过程中的激活值,首先以改进的核密度估计技术构建神经元的激活分布,模拟神经元的正常工作范围.接着采用邻域加权密度估计方法计算异常因子,用以量化测试样本与神经元激活分布的偏离程度.最终通过统计方法综合各神经元的异常因子作为样本的异常统计量,为模型不确定性的评估提供新的视角.实验结果涵盖多个公开数据集和模型,通过可视化特征图直观展示本文方法在区分域内外样本方面的显著效果.此外,本文方法在域外检测任务中表现出卓越性能,AUROC指标在多种实验设置下均超越其他现有方法,验证提出方法的通用性和有效性.
Abstract
The uncertainty of neural networks reflects the predictive confidence of deep learning models,enabling timely human intervention in unreliable decision-making,which is crucial for enhancing system safety.However,existing measurement methods often require significant modifications to the model or training process,leading to high implementation complexity.To address this,this study proposes an uncertainty measurement approach utilizing neuron statistical modeling and analysis with activation values within a single forward propagation.An improved kernel density estimation technology is employed to construct neuron activation distributions and stimulate neuron normal operating range.Subsequently,a neighborhood-weighted density estimation method is utilized to calculate anomaly factors,effectively qualifying deviations of test samples from neuron activation distribution.Finally,by statistically combining the anomaly factors of each neuron,the cumulative anomaly factors of the sample provide a new perspective in assessing model uncertainty.Experimental results across multiple public datasets and models visually demonstrate the significant effectiveness of the proposed method in distinguishing between in-domain and out-of-domain samples through visualizing feature maps.Moreover,the method exhibits exceptional performance in out-of-domain detection tasks,with AUROC exceeding other methods across various experimental setups,validating its generality and effectiveness.
关键词
不确定性分析/深度学习/激活分布/异常因子/域外检测Key words
uncertainty analysis/deep learning/activation distribution/anomaly factor/out-of-domain detection引用本文复制引用
基金项目
国家自然科学基金(62106051)
上海浦江计划(21PJ1400600)
国家重点研发计划(2022YFC3601405)
上海研究与创新功能项目(17DZ2260900)
出版年
2024
NETL
NSTL
万方数据