GMMCL: Adaptive Concept Drift in Data Streams with Gaussian Mixture Models based on Contrastive Learning

Hongwei Wu; Jin Pan; Rong Yang; Hong Zhang; Guang Shi; Zhuojun Jiang; Qingyun Liu

ICASSP 2025accepted0 citations

GMMCL: Adaptive Concept Drift in Data Streams with Gaussian Mixture Models based on Contrastive Learning

Hongwei Wu, Jin Pan, Rong Yang, Hong Zhang, Guang Shi, Zhuojun Jiang, Qingyun Liu

Abstract

Classical classification methods often fail in dynamic environments where data distributions shift over time, known as concept drift. Applications like flight delay prediction and weather forecasting require handling such dynamic data streams. Concept drift can be either virtual, affecting unconditional probability distributions, or real, affecting conditional distributions. While most research focuses on real drift, virtual drift and noise also degrade classifier performance. In this paper, we propose gaussian mixture models based on contrastive learning (GMMCL), a novel approach that integrates noise handling, contrastive learning, drift detection, and gaussian mixture models. Our method significantly enhances adaptability to noisy and drifting data streams, outperforming mainstream approaches across twelve synthetic and real-world datasets. This provides a robust solution for managing concept drift and noise in dynamic classification tasks.

BibTeX

@inproceedings{icassp2025_gmmcladaptivecon,
  title = {GMMCL: Adaptive Concept Drift in Data Streams with Gaussian Mixture Models based on Contrastive Learning},
  author = {Hongwei Wu and Jin Pan and Rong Yang and Hong Zhang and Guang Shi and Zhuojun Jiang and Qingyun Liu},
  booktitle = {ICASSP 2025},
  year = {2025}
}