# Interpretable Model Drift Detection

arXiv: https://arxiv.org/abs/2503.06606 · HTML: https://mlsanity.com/paper/2503.06606/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 48 references that are in the map.
- First posted on arXiv 9 Mar 2025.

## Builds on (most cited first, 11 of 11)

- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Learning under Concept Drift: A Review](https://mlsanity.com/paper/2004.05785/) (2020)
- [Robust and Stable Black Box Explanations](https://mlsanity.com/paper/2011.06169/) (2020)
- [Reactive Soft Prototype Computing for Concept Drift Streams](https://mlsanity.com/paper/2007.05432/) (2020)
- [Feature Shift Detection: Localizing Which Features Have Shifted via Conditional Distribution Tests](https://mlsanity.com/paper/2107.06929/) (2021)
- [McDiarmid Drift Detection Methods for Evolving Data Streams](https://mlsanity.com/paper/1710.02030/) (2017)
- [A Survey on Concept Drift in Process Mining](https://mlsanity.com/paper/2112.02000/) (2021)
- [Request-and-Reverify: Hierarchical Hypothesis Testing for Concept Drift Detection with Expensive Labels](https://mlsanity.com/paper/1806.10131/) (2018)
- [Addressing machine learning concept drift reveals declining vaccine sentiment during the COVID-19 pandemic](https://mlsanity.com/paper/2012.02197/) (2020)
- [DriftSurf: A Risk-competitive Learning Algorithm under Concept Drift](https://mlsanity.com/paper/2003.06508/) (2020)
- [CURIE: A Cellular Automaton for Concept Drift Detection](https://mlsanity.com/paper/2009.09677/) (2020)

## Built on by (most cited first, 1 of 1)

- ["Who experiences large model decay and why?" A Hierarchical Framework for Diagnosing Heterogeneous Performance Drift](https://mlsanity.com/paper/2506.00756/) (2025)

## Abstract (arXiv)

Data in the real world often has an evolving distribution. Thus, machine learning models trained on such data get outdated over time. This phenomenon is called model drift. Knowledge of this drift serves two purposes: (i) Retain an accurate model and (ii) Discovery of knowledge or insights about change in the relationship between input features and output variable w.r.t. the model. Most existing works focus only on detecting model drift but offer no interpretability. In this work, we take a principled approach to study the problem of interpretable model drift detection from a risk perspective using a feature-interaction aware hypothesis testing framework, which enjoys guarantees on test power. The proposed framework is generic, i.e., it can be adapted to both classification and regression tasks. Experiments on several standard drift detection datasets show that our method is superior to existing interpretable methods (especially on real-world datasets) and on par with state-of-the-art black-box drift detection methods. We also quantitatively and qualitatively study the interpretability aspect including a case study on USENET2 dataset. We find our method focuses on model and drift sensitive features compared to baseline interpretable drift detectors.