Characterizing Concept Drift

TL;DR

This paper develops a comprehensive framework and formal definitions for characterizing and categorizing different types of concept drift in machine learning, addressing a key gap in understanding non-stationary data.

Contribution

It introduces the first formal, quantitative framework for analyzing concept drift, establishing a taxonomy and clarifying ambiguities in previous qualitative categorizations.

Findings

First formal definitions of concept drift types

A comprehensive taxonomy of concept drift

Clarification of ambiguities in previous definitions

Abstract

Most machine learning models are static, but the world is dynamic, and increasing online deployment of learned models gives increasing urgency to the development of efficient and effective mechanisms to address learning in the context of non-stationary distributions, or as it is commonly called concept drift. However, the key issue of characterizing the different types of drift that can occur has not previously been subjected to rigorous definition and analysis. In particular, while some qualitative drift categorizations have been proposed, few have been formally defined, and the quantitative descriptions required for precise and objective understanding of learner performance have not existed. We present the first comprehensive framework for quantitative analysis of drift. This supports the development of the first comprehensive set of formal definitions of types of concept drift. The formal definitions clarify ambiguities and identify gaps in previous definitions, giving rise to a new comprehensive taxonomy of concept drift types and a solid foundation for research into mechanisms to detect and address concept drift.