Accumulating regional density dissimilarity for concept drift detection in data streams

作者：Liu Anjin; Lu Jie^*; Liu Feng; Zhang Guangquan

来源：Pattern Recognition, 2018, 76: 256-272.

DOI：10.1016/j.patcog.2017.11.009

• Concept drift
• Dataset shift
• Changing environments
• Covariate shift
• Empirical density estimation

In a non-stationary environment, newly received data may have different knowledge patterns from the data used to train learning models. As time passes, a learning model's performance may become increasingly unreliable. This problem is known as concept drift and is a common issue in real-world domains. Concept drift detection has attracted increasing attention in recent years. However, very few existing methods pay attention to small regional drifts, and their accuracy may vary due to differing statistical significance tests. This paper presents a novel concept drift detection method, based on regional-density estimation, named nearest neighbor-based density variation identification (NN-DVI). It consists of three components. The first is a k-nearest neighbor-based space-partitioning schema (NNPS), which transforms unmeasurable discrete data instances into a set of shared subspaces for density estimation. The second is a distance function that accumulates the density discrepancies in these subspaces and quantifies the overall differences. The third component is a tailored statistical significance test by which the confidence interval of a concept drift can be accurately determined. The distance applied in NN-DVI is sensitive to regional drift and has been proven to follow a normal distribution. As a result, the NN-DVI's accuracy and false-alarm rate are statistically guaranteed. Additionally, several benchmarks have been used to evaluate the method, including both synthetic and real-world datasets. The overall results show that NN-DVI has better performance in terms of addressing problems related to concept drift-detection.

• 出版日期2018-4