# Unsupervised Unlearning of Concept Drift with Autoencoders

arXiv: https://arxiv.org/abs/2211.12989 · HTML: https://mlsanity.com/paper/2211.12989/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 38 references that are in the map.
- First posted on arXiv 23 Nov 2022.

## Builds on (most cited first, 10 of 10)

- [A Comprehensive Survey on Transfer Learning](https://mlsanity.com/paper/1911.02685/) (2019)
- [A Systematic Study of Online Class Imbalance Learning with Concept Drift](https://mlsanity.com/paper/1703.06683/) (2017)
- [Online Learning With Adaptive Rebalancing in Nonstationary Environments](https://mlsanity.com/paper/2009.11942/) (2020)
- [Nonstationary data stream classification with online active learning and siamese neural networks](https://mlsanity.com/paper/2210.01090/) (2022)
- [Unsupervised Transfer Learning for Spatiotemporal Predictive Networks](https://mlsanity.com/paper/2009.11763/) (2020)
- [Queue-based Resampling for Online Class Imbalance Learning](https://mlsanity.com/paper/1809.10388/) (2018)
- [A Hybrid Active-Passive Approach to Imbalanced Nonstationary Data Stream Classification](https://mlsanity.com/paper/2210.04949/) (2022)
- [Learning Invariant Representation for Continual Learning](https://mlsanity.com/paper/2101.06162/) (2021)
- [Data augmentation on-the-fly and active learning in data stream classification](https://mlsanity.com/paper/2210.06873/) (2022)
- [SAM-kNN Regressor for Online Learning in Water Distribution Networks](https://mlsanity.com/paper/2204.01436/) (2022)

## Built on by (most cited first, 3 of 3)

- [Incremental Learning with Concept Drift Detection and Prototype-based Embeddings for Graph Stream Classification](https://mlsanity.com/paper/2404.02572/) (2024)
- [SiameseDuo++: Active Learning from Data Streams with Dual Augmented Siamese Networks](https://mlsanity.com/paper/2504.04613/) (2025)
- [Autonomous Drift Learning in Data Streams: A Unified Perspective](https://mlsanity.com/paper/2605.01295/) (2026)

## Abstract (arXiv)

Concept drift refers to a change in the data distribution affecting the data stream of future samples. Consequently, learning models operating on the data stream might become obsolete, and need costly and difficult adjustments such as retraining or adaptation. Existing methods usually implement a local concept drift adaptation scheme, where either incremental learning of the models is used, or the models are completely retrained when a drift detection mechanism triggers an alarm. This paper proposes an alternative approach in which an unsupervised and model-agnostic concept drift adaptation method at the global level is introduced, based on autoencoders. Specifically, the proposed method aims to ``unlearn'' the concept drift without having to retrain or adapt any of the learning models operating on the data. An extensive experimental evaluation is conducted in two application domains. We consider a realistic water distribution network with more than 30 models in-place, from which we create 200 simulated data sets / scenarios. We further consider an image-related task to demonstrate the effectiveness of our method.