SOMtime the World Ain$'$t Fair: Violating Fairness Using Self-Organizing Maps
Joseph Bingham, Netanel Arussy, Dvir Aran

TL;DR
This paper reveals that unsupervised representations, specifically those produced by Self-Organizing Maps, can inadvertently encode sensitive attributes like age and income, challenging the assumption of neutrality and highlighting the need for fairness auditing beyond supervised tasks.
Contribution
It demonstrates that high-capacity unsupervised models like SOMtime can recover sensitive attribute information, showing that fairness through unawareness fails at the representation level.
Findings
SOMtime recovers monotonic orderings of sensitive attributes with high correlation (up to 0.85).
Unsupervised segmentation produces demographically skewed clusters.
Traditional dimensionality reduction methods show lower correlation with sensitive attributes.
Abstract
Unsupervised representations are widely assumed to be neutral with respect to sensitive attributes when those attributes are withheld from training. We show that this assumption is false. Using SOMtime, a topology-preserving representation method based on high-capacity Self-Organizing Maps, we demonstrate that sensitive attributes such as age and income emerge as dominant latent axes in purely unsupervised embeddings, even when explicitly excluded from the input. On two large-scale real-world datasets (the World Values Survey across five countries and the Census-Income dataset), SOMtime recovers monotonic orderings aligned with withheld sensitive attributes, achieving Spearman correlations of up to 0.85, whereas PCA and UMAP typically remain below 0.23 (with a single exception reaching 0.31), and against t-SNE and autoencoders which achieve at most 0.34. Furthermore, unsupervised…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsEthics and Social Impacts of AI · Explainable Artificial Intelligence (XAI) · Artificial Intelligence Applications
