# Request-and-Reverify: Hierarchical Hypothesis Testing for Concept Drift Detection with Expensive Labels

arXiv: https://arxiv.org/abs/1806.10131 · HTML: https://mlsanity.com/paper/1806.10131/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jun 2018.

## Built on by (most cited first, 11 of 11)

- [Feature Shift Detection: Localizing Which Features Have Shifted via Conditional Distribution Tests](https://mlsanity.com/paper/2107.06929/) (2021)
- [STUDD: A Student-Teacher Method for Unsupervised Concept Drift Detection](https://mlsanity.com/paper/2103.00903/) (2021)
- [MLDemon: Deployment Monitoring for Machine Learning Systems](https://mlsanity.com/paper/2104.13621/) (2021)
- [Detecting Rumours with Latency Guarantees using Massive Streaming Data](https://mlsanity.com/paper/2205.06580/) (2022)
- [MLHOps: Machine Learning for Healthcare Operations](https://mlsanity.com/paper/2305.02474/) (2023)
- [Adversarial Learning for Feature Shift Detection and Correction](https://mlsanity.com/paper/2312.04546/) (2023)
- [A Comprehensive Review of Machine Learning Advances on Data Change: A Cross-Field Perspective](https://mlsanity.com/paper/2402.12627/) (2024)
- [A Neighbor-Searching Discrepancy-based Drift Detection Scheme for Learning Evolving Data](https://mlsanity.com/paper/2405.14153/) (2024)
- [Interpretable Model Drift Detection](https://mlsanity.com/paper/2503.06606/) (2025)
- [On the Connection between Concept Drift and Uncertainty in Industrial Artificial Intelligence](https://mlsanity.com/paper/2303.07940/) (2023)
- [Feature Shift Localization Network](https://mlsanity.com/paper/2506.09101/) (2025)

## Abstract (arXiv)

One important assumption underlying common classification models is the stationarity of the data. However, in real-world streaming applications, the data concept indicated by the joint distribution of feature and label is not stationary but drifting over time. Concept drift detection aims to detect such drifts and adapt the model so as to mitigate any deterioration in the model's predictive performance. Unfortunately, most existing concept drift detection methods rely on a strong and over-optimistic condition that the true labels are available immediately for all already classified instances. In this paper, a novel Hierarchical Hypothesis Testing framework with Request-and-Reverify strategy is developed to detect concept drifts by requesting labels only when necessary. Two methods, namely Hierarchical Hypothesis Testing with Classification Uncertainty (HHT-CU) and Hierarchical Hypothesis Testing with Attribute-wise "Goodness-of-fit" (HHT-AG), are proposed respectively under the novel framework. In experiments with benchmark datasets, our methods demonstrate overwhelming advantages over state-of-the-art unsupervised drift detectors. More importantly, our methods even outperform DDM (the widely used supervised drift detector) when we use significantly fewer labels.