提出新鲁棒性度量，让任意判别模型都能评估预测可靠性。
Robustness Quantification for Discriminative Models: a New Robustness Metric and its Application to Dynamic Classifier Selection
- 基于概率判别模型设计通用鲁棒性度量
- 能有效区分可靠与不可靠预测结果
- 适用于动态分类器选择场景
在评估分类器个体预测可靠性时，鲁棒性量化因其能衡量分类器在改变预测前可承受的不确定性而脱颖而出。然而，其应用受限于需使用生成模型，且分析范围仅限特定模型架构或离散特征。本文提出一种适用于任意概率判别模型及任意特征类型的新型鲁棒性度量。实验表明该度量能有效区分可靠与不可靠预测，并据此开发出新的动态分类器选择策略。
原文摘要 · Abstract (English)
Among the different possible strategies for evaluating the reliability of individual predictions of classifiers, robustness quantification stands out as a method that evaluates how much uncertainty a classifier could cope with before changing its prediction. However, its applicability is more limited than some of its alternatives, since it requires the use of generative models and restricts the analyses either to specific model architectures or discrete features. In this work, we propose a new robustness metric applicable to any probabilistic discriminative classifier and any type of features. We demonstrate that this new metric is capable of distinguishing between reliable and unreliable predictions, and use this observation to develop new strategies for dynamic classifier selection.
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。