Change Detection for Local Explainability in Evolving Data Streams

TL;DR

This paper addresses the challenge of maintaining reliable local explanations in evolving data streams by proposing a framework that detects local and global concept drift to update attributions accordingly.

Contribution

We introduce CDLEEDS, a model-agnostic framework that detects local change and concept drift, enhancing the robustness of local explanations in streaming data environments.

Findings

CDLEEDS reliably detects local and global concept drift.

Local attributions become outdated with model updates or data shifts.

Framework improves the relevance of explanations over time.

Abstract

As complex machine learning models are increasingly used in sensitive applications like banking, trading or credit scoring, there is a growing demand for reliable explanation mechanisms. Local feature attribution methods have become a popular technique for post-hoc and model-agnostic explanations. However, attribution methods typically assume a stationary environment in which the predictive model has been trained and remains stable. As a result, it is often unclear how local attributions behave in realistic, constantly evolving settings such as streaming and online applications. In this paper, we discuss the impact of temporal change on local feature attributions. In particular, we show that local attributions can become obsolete each time the predictive model is updated or concept drift alters the data generating distribution. Consequently, local feature attributions in data streams provide high explanatory power only when combined with a mechanism that allows us to detect and respond to local changes over time. To this end, we present CDLEEDS, a flexible and model-agnostic framework for detecting local change and concept drift. CDLEEDS serves as an intuitive extension of attribution-based explanation techniques to identify outdated local attributions and enable more targeted recalculations. In experiments, we also show that the proposed framework can reliably detect both local and global concept drift. Accordingly, our work contributes to a more meaningful and robust explainability in online machine learning.