An overview of unsupervised drift detection methods

Abstract

Practical applications involving big data, such as weather monitoring, identification of customer preferences, Internet log analysis, and sensors warnings require challenging data analysis, since these are examples of problems whose data are generated in streams and usually demand real-time analytics. Patterns in such data stream problems may change quickly. Consequently, machine learning models that operate in this context must be updated over time. This phenomenon is called concept drift in machine learning and data mining literature. Several different directions have been pursued to learn from data stream and to deal with concept drift. However, most drift detection methods consider that an instance's class label is available right after its prediction, since these methods work by monitoring the prediction results of a base classifier or an ensemble of classifiers. Nevertheless, this constraint is unrealistic in several practical problems. To cope with this constraint, some works are focused on proposing efficient unsupervised or semi-supervised concept drift detectors. While interesting and recent overview papers dedicated to supervised drift detectors have been published, the scenario is not the same in terms of unsupervised methods. Therefore, this work presents a comprehensive overview of approaches that tackle concept drift in classification problems in an unsupervised manner. Additional contribution includes a proposed taxonomy of state-of-the-art approaches for concept drift detection based on unsupervised strategies.

Implicit Concept Drift Detection for Multi-label Data Streams

“…Iwashita and Papa (2018) found that unsupervised drift detectors only make up 3% of developed concept drift detectors. However, as Gemaque et al point out, many of the real-world problems are better suited for unsupervised drift detection, since the swift acquisition of labels is often not possible (Gemaque et al, 2020). Since concept drift detection requires fast detection to enable rapid recovery after drift, the topic of unsupervised concept drift detection requires more attention.…”

From Concept Drift to Model Degradation: An Overview on Performance-Aware Drift Detectors

“…Besides these review papers in the literature, other papers explored handling concept drift in specific learning tasks. A recently published review paper by Gemaque et al [42] provides a full-scale overview of the methods that handle concept drift in unsupervised learning. Other papers review and scrutinize the progress in class-imbalanced data streams [43,4].…”

Concept Drift Adaptation with Incremental–Decremental SVM

“…Several models addressing concept drift on adaptive windows were proposed in recent years. Detailed overviews are given by the work of Iwashita et al [5], Lu et al [6], as well as Gemaque et al [21]. The Learn++.NSE algorithm [22,23] and its fast version [24] generate a new classifier for each received batch of data, and add the classifier to an existing ensemble.…”