A survey on concept drift adaptation
Обзор адаптации к дрейфу концепций
2014-03-01
SCID: 54.1/pn675975
Discuss with AI
adaptive algorithm evaluationadaptive learningconcept drift adaptationconcept drift detectiononline supervised learning
Figures from the paper
Abstract (AI)
Concept drift primarily refers to an online supervised learning scenario when the relation between the input data and the target variable changes over time. Assuming a general knowledge of supervised learning in this article, we characterize adaptive learning processes; categorize existing strategies for handling concept drift; overview the most representative, distinct, and popular techniques and algorithms; discuss evaluation methodology of adaptive algorithms; and present a set of illustrative applications. The survey covers the different facets of concept drift in an integrated way to reflect on the existing scattered state of the art. Thus, it aims at providing a comprehensive introduction to the concept drift adaptation for researchers, industry analysts, and practitioners.
Key Findings
1
Concept drift is defined as an online supervised-learning setting where the relationship between input data and target variables changes over time.
2
It reviews representative, distinct, and widely used techniques and algorithms for concept-drift adaptation.
3
The paper discusses evaluation methodologies for adaptive algorithms and presents illustrative applications.
4
The survey characterizes adaptive learning processes and categorizes existing strategies for handling concept drift.
5
The survey integrates fragmented research on concept drift adaptation into a comprehensive introduction for researchers and practitioners.
Research Object
Concept drift in online supervised learning
Research Subject
adaptation strategies, learning processes, algorithms, and evaluation methods for handling concept drift
Publication Details
Publication Date
2014-03-01
Journal
Publisher
ISSN
Cited by
3740
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai1
Cited by10
Machine learning and deep learning2021
A Review on Outlier/Anomaly Detection in Time Series Data2021
Unsupervised real-time anomaly detection for streaming data2017
Financial Fraud: A Review of Anomaly Detection Techniques and Recent Advances2021
Concept Drift Detection in Data Stream Mining : A literature review2021
Data stream mining: methods and challenges for handling concept drift2019
FraudGNN-RL: A Graph Neural Network With Reinforcement Learning for Adaptive Financial Fraud Detection2025
No More Labelled Examples? An Unsupervised Log Parser with LLMs2025
Analyzing the impact of shifts in encrypted mobile-app traffic on multimodal few-shot learning2025
Trustworthy Agentic Supply Chains: A Governance Framework for Digital Twin Orchestrated AI Decisioning Under Compliance, Auditability, and Data Sovereignty Constraints2026