A Neighbor-Searching Discrepancy-based Drift Detection Scheme for Learning Evolving Data

TL;DR

This paper introduces a novel drift detection method based on Neighbor-Searching Discrepancy that accurately identifies real concept drift in data streams, distinguishes it from virtual drift, and provides trend information for better model maintenance.

Contribution

The paper proposes a new discrepancy-based statistic for real concept drift detection that outperforms existing methods and offers insights into the direction of drift.

Findings

High accuracy in detecting real concept drift

Effective in ignoring virtual drift

Outperforms state-of-the-art methods in experiments

Abstract

Uncertain changes in data streams present challenges for machine learning models to dynamically adapt and uphold performance in real-time. Particularly, classification boundary change, also known as real concept drift, is the major cause of classification performance deterioration. However, accurately detecting real concept drift remains challenging because the theoretical foundations of existing drift detection methods - two-sample distribution tests and monitoring classification error rate, both suffer from inherent limitations such as the inability to distinguish virtual drift (changes not affecting the classification boundary, will introduce unnecessary model maintenance), limited statistical power, or high computational cost. Furthermore, no existing detection method can provide information on the trend of the drift, which could be invaluable for model maintenance. This work presents a novel real concept drift detection method based on Neighbor-Searching Discrepancy, a new statistic that measures the classification boundary difference between two samples. The proposed method is able to detect real concept drift with high accuracy while ignoring virtual drift. It can also indicate the direction of the classification boundary change by identifying the invasion or retreat of a certain class, which is also an indicator of separability change between classes. A comprehensive evaluation of 11 experiments is conducted, including empirical verification of the proposed theory using artificial datasets, and experimental comparisons with commonly used drift handling methods on real-world datasets. The results show that the proposed theory is robust against a range of distributions and dimensions, and the drift detection method outperforms state-of-the-art alternative methods.