用置信预测定位数据分布漂移，提升高维场景检测精度
Drift Localization using Conformal Predictions
- 基于置信预测构建全局漂移检测框架，避免局部检验失效
- 在ImageNet等主流图像数据集上验证有效，适应低信号高维环境
- 适合需要实时监控模型性能的部署系统使用
概念漂移——随时间变化的数据分布——给学习系统带来重大挑战，是监测的核心关注点。理解漂移至关重要，而漂移定位——确定哪些样本受漂移影响——尤为关键。尽管已有多种方法，但多数依赖局部检验，往往在高维、低信号场景下表现不佳。本文提出一种根本不同的方法，基于置信预测。我们分析并揭示了现有方法的局限性，并在最先进的图像数据集上展示了所提方法的性能。
原文摘要 · Abstract (English)
Concept drift -- the change of the distribution over time -- poses significant challenges for learning systems and is of central interest for monitoring. Understanding drift is thus paramount, and drift localization -- determining which samples are affected by the drift -- is essential. While several approaches exist, most rely on local testing schemes, which tend to fail in high-dimensional, low-signal settings. In this work, we consider a fundamentally different approach based on conformal predictions. We discuss and show the shortcomings of common approaches and demonstrate the performance of our approach on state-of-the-art image datasets.
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。