跳到正文
arXiv cs.AI· Ronaldo C. Prati, Elaine Ribeiro de Faria·· 4 小时前AI 评分31

面向延迟标签与分布漂移的数据流评估时间代数框架

A Temporal Algebraic Framework for Data Stream Evaluation Under Delayed Labels and Distribution Shifts

AI 导读

研究者扩展了一个代数框架,用指数衰减或滑动窗口对时间上的计数加权,从单一混淆矩阵同时得到数据流的池化(micro)与逐类(macro)指标,每步更新成本为 O(m^2) 且与流长度无关。

正文 · 原文

View PDF HTML (experimental)

Abstract:In data streams, labels often arrive late or only for some instances, class prevalence drifts, and rare classes vanish from short windows. Standard evaluation then confuses a degraded decision boundary with a change in prevalence, and is biased when labels are delayed or selected by the model. We extend an algebraic framework that obtains pooled (micro) and per-class (macro) measures from one confusion matrix to streams, weighting the counts in time by exponential fading or a sliding window; the update costs O(m^2) per step, whatever the stream length, and each pooled measure stays a weighted combination of the per-class ones. Delayed and selective feedback enter as an observation mask: until its label arrives, an instance is counted with the model's calibrated class probabilities, and the bias of this interim estimate is driven by their calibration error. Audited conventions report no value for a class without verified instances. We separate prior shift from concept drift by monitoring prior-free coordinates (recall and specificity) and attribute a change in a measure to the two sources with a first-order Jacobian decomposition. On synthetic streams and four real datasets, a detector on these coordinates with a memory per class raises no excess false alarms under label shift, unlike the Jacobian alarm and error-rate detectors. The correction for delayed labels recovers recall in some real settings and is only partial for precision, specificity and F1. Twenty-five statements are checked in Lean 4, and the code is in the aggmetrics package.
Comments: 53 pages, 25 tables, 2 figures. Code: this https URL (experiments), this https URL (Lean 4 formalization), this https URL (aggmetrics >= 0.4.0, subpackage this http URL)
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Databases (cs.DB)
MSC classes: 68T05, 62H30, 62L10, 68V20
ACM classes: I.2.6; H.2.8; G.3
Cite as: arXiv:2611.21914 [cs.LG]
  (or arXiv:2611.21914v1 [cs.LG] for this version)
  https://doi.org/10.48550/arXiv.2611.21914

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Ronaldo Prati [view email]
[v1] Mon, 16 Nov 2026 21:28:59 UTC (301 KB)

来源:arXiv cs.AI · arxiv.org