Unsupervised Unlearning of Concept Drift with Autoencoders
This addresses the costly adaptation of learning models to distribution changes, offering a global solution for domains like infrastructure monitoring, though it appears incremental as it builds on autoencoder-based approaches.
The paper tackles the problem of concept drift in data streams by proposing an unsupervised, model-agnostic method using autoencoders to 'unlearn' drift without retraining models, achieving effectiveness demonstrated in water distribution networks with 200 simulated datasets and an image task.
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.