iSAGE: An Incremental Version of SAGE for Online Explanation on Data Streams
This work addresses the need for real-time explainability in streaming data applications, offering an incremental solution for practitioners in fields like finance or IoT, though it is incremental as it adapts an existing method to a new scenario.
The paper tackles the problem of explaining machine learning models in dynamic environments where data arrives continuously, by proposing iSAGE, an incremental version of SAGE that efficiently updates feature importance explanations online, achieving significant speed-ups and memory savings in experiments.
Existing methods for explainable artificial intelligence (XAI), including popular feature importance measures such as SAGE, are mostly restricted to the batch learning scenario. However, machine learning is often applied in dynamic environments, where data arrives continuously and learning must be done in an online manner. Therefore, we propose iSAGE, a time- and memory-efficient incrementalization of SAGE, which is able to react to changes in the model as well as to drift in the data-generating process. We further provide efficient feature removal methods that break (interventional) and retain (observational) feature dependencies. Moreover, we formally analyze our explanation method to show that iSAGE adheres to similar theoretical properties as SAGE. Finally, we evaluate our approach in a thorough experimental analysis based on well-established data sets and data streams with concept drift.