通过层间最近邻激活相似性，量化神经网络决策不确定性。
A Framework for Uncertainty Quantification Based on Nearest Neighbors Across Layers
- 基于各层激活向量的最近邻检索，构建不确定性度量框架。
- 在CIFAR-10和MNIST上，新指标显著优于Softmax置信度。
- 适合高风险场景中的模型可信度评估，如医疗诊断。
神经网络在难以建模或发现模式的问题中表现优异，但有时会给出错误结果，这在医疗诊断、自动驾驶等高风险领域尤为危险。一种应对策略是量化神经网络决策的不确定性。本文提出一种新的后处理框架，通过检索与查询样本在各层具有相似激活向量的训练样本，来衡量决策不确定性。基于这些检索到的样本，我们提出了两个新指标：决策变化（Decision Change）和层不确定性（Layer Uncertainty），用于捕捉最近邻类别分布随层变化的情况。我们在两个数据集（CIFAR-10 和 MNIST）上的分类模型中评估了该方法，结果表明，这些指标能有效提升不确定性估计性能，尤其在复杂分类任务中优于基于Softmax的置信度。
原文摘要 · Abstract (English)
Neural Networks have high accuracy in solving problems where it is difficult to detect patterns or create a logical model. However, these algorithms sometimes return wrong solutions, which become problematic in high-risk domains like medical diagnosis or autonomous driving. One strategy to detect and mitigate these errors is the measurement of the uncertainty over neural network decisions. In this paper, we present a novel post-hoc framework for measuring the uncertainty of a decision based on retrieved training cases that have a similar activation vector to the query for each layer. Based on these retrieved cases, we propose two new metrics: Decision Change and Layer Uncertainty, which capture changes in nearest-neighbor class distributions across layers. We evaluated our approach in a classification model for two datasets: CIFAR-10 and MNIST. The results show that these metrics enhance uncertainty estimation, especially in challenging classification tasks, outperforming softmax-based confidence.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。