Sanitized clustering against confounding bias

Yinghua YAO, Yuangang PAN, Jing LI, Ivor W. TSANG*, Xin YAO*

*Corresponding author for this work

Research output: Journal PublicationsJournal Article (refereed)peer-review


Real-world datasets inevitably contain biases that arise from different sources or conditions during data collection. Consequently, such inconsistency itself acts as a confounding factor that disturbs the cluster analysis. Existing methods eliminate the biases by projecting data onto the orthogonal complement of the subspace expanded by the confounding factor before clustering. Therein, the interested clustering factor and the confounding factor are coarsely considered in the raw feature space, where the correlation between the data and the confounding factor is ideally assumed to be linear for convenient solutions. These approaches are thus limited in scope as the data in real applications is usually complex and non-linearly correlated with the confounding factor. This paper presents a new clustering framework named Sanitized Clustering Against confounding Bias, which removes the confounding factor in the semantic latent space of complex data through a non-linear dependence measure. To be specific, we eliminate the bias information in the latent space by minimizing the mutual information between the confounding factor and the latent representation delivered by variational auto-encoder. Meanwhile, a clustering module is introduced to cluster over the purified latent representations. Extensive experiments on complex datasets demonstrate that our SCAB achieves a significant gain in clustering performance by removing the confounding bias.

Original languageEnglish
Number of pages20
JournalMachine Learning
Publication statusE-pub ahead of print - 27 Dec 2023
Externally publishedYes

Bibliographical note

Publisher Copyright:
© 2023, The Author(s).


  • Confounding bias
  • Deep clustering
  • Mutual information
  • Non-linear dependence


Dive into the research topics of 'Sanitized clustering against confounding bias'. Together they form a unique fingerprint.

Cite this