# Concept Drift from a Causal Perspective

arXiv: https://arxiv.org/abs/2609.25340 · HTML: https://mlsanity.com/paper/2609.25340/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 57 references that are in the map.
- First posted on arXiv 21 Sep 2026.

## Builds on (most cited first, 21 of 21)

- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [Out-of-Distribution Generalization via Risk Extrapolation (REx)](https://mlsanity.com/paper/2003.00688/) (2020)
- [Causal inference using invariant prediction: identification and confidence intervals](https://mlsanity.com/paper/1501.01332/) (2015)
- [Learning under Concept Drift: A Review](https://mlsanity.com/paper/2004.05785/) (2020)
- [The Risks of Invariant Risk Minimization](https://mlsanity.com/paper/2010.05761/) (2020)
- [Detecting causal associations in large nonlinear time series datasets](https://mlsanity.com/paper/1702.07007/) (2017)
- [A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms](https://mlsanity.com/paper/1901.10912/) (2019)
- [DoWhy: An End-to-End Library for Causal Inference](https://mlsanity.com/paper/2011.04216/) (2020)
- [Probable Domain Generalization via Quantile Risk Minimization](https://mlsanity.com/paper/2207.09944/) (2022)
- [Unifying Causal Representation Learning with the Invariance Principle](https://mlsanity.com/paper/2409.02772/) (2024)
- [Detecting Concept Drift With Neural Network Model Uncertainty](https://mlsanity.com/paper/2107.01873/) (2021)
- [Causal discovery for time series from multiple datasets with latent contexts](https://mlsanity.com/paper/2306.12896/) (2023)
- [McDiarmid Drift Detection Methods for Evolving Data Streams](https://mlsanity.com/paper/1710.02030/) (2017)
- [CauKer: Classification Time Series Foundation Models Can Be Pretrained on Synthetic Data](https://mlsanity.com/paper/2508.02879/) (2025)
- [Early Concept Drift Detection via Prediction Uncertainty](https://mlsanity.com/paper/2412.11158/) (2024)
- [A Statistical Approach to Adult Census Income Level Prediction](https://mlsanity.com/paper/1810.10076/) (2018)
- [Causal Discovery in Semi-Stationary Time Series](https://mlsanity.com/paper/2407.07291/) (2024)
- [Identifying General Mechanism Shifts in Linear Causal Representations](https://mlsanity.com/paper/2410.24059/) (2024)
- [Synthetic Non-stationary Data Streams for Recognition of the Unknown](https://mlsanity.com/paper/2505.13745/) (2025)
- [IncA-DES: An incremental and adaptive dynamic ensemble selection approach using online K-d tree neighborhood search for data streams with concept drift](https://mlsanity.com/paper/2507.12573/) (2025)
- [The Window Dilemma: Why Concept Drift Detection is Ill-Posed](https://mlsanity.com/paper/2602.06456/) (2026)

## Abstract (arXiv)

Concept drift is a common phenomenon in real-world data streams, in which changes in the data-generating distribution can degrade predictive model performance. Most existing definitions characterize drift as changes in the joint distribution P(x, y), without distinguishing which component of the data-generating process has changed. In this work, we introduce a causal perspective on concept drift based on Structural Causal Models (SCMs). We propose a taxonomy that categorizes drift events by their causal origin, including changes in exogenous variables, endogenous mechanisms, confounders, and target-generating processes. Building on this framework, we develop an SCM-based data stream generator that simulates controlled mechanism-level drift events. Our experiments empirically characterize the distributional effects of each drift type and show that drifts with different causal origins induce distinct patterns of distribution shift and predictive behavior. Furthermore, by integrating causal discovery methods, we use our framework to construct data streams grounded in real-world dependency structures, enabling more realistic and informative evaluation scenarios. We also demonstrate that leveraging the generated data can improve downstream performance. These results highlight the importance of accounting for causal structure when studying and evaluating adaptive learning methods, and establish a foundation for causally-aware evaluation in non-stationary environments.