Concepts have recently gained attention as an explainable AI (XAI) tool because of their human interpretability. While recent work shows that concepts can provide meaningful explanations for high-dimensional data drift, many open questions remain. This topic offers several directions, such as studying the properties of the embeddings required for concept extraction, adapting concept-based drift localization to online settings, extending the current approach from images to different data domains such as text, or developing new methods for detecting drift directly through concepts.

Literature

1. Fel, Thomas, et al. “Craft: Concept recursive activation factorization for explainability.”
2. Hinder, Fabian et al. “Model-based explanations of concept drift”
3. Roberts, Isaac et al. “Conceptualizing Concept Drift”