AI Paper Atlas

Research map / Learning theory and algorithms / Fairness

Position: Fair Representations Cannot Hold What They Promise

Shai Ben-David, Tosca Lechner, Ruth Urner

NeurIPS 2026 · Learning theory and algorithms › Fairness · approach: Post-processing and transport for fairness

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Position paper arguing that fair representation learning cannot deliver the fairness guarantees its papers imply for downstream tasks.

Problem

Fair representation learning is widely presented as a data preprocessing route to fairness for downstream tasks, but the abstract suggests these promises may not hold.

Approach

Critically argues that fair representations cannot hold the fairness promises made in the literature; the abstract does not specify the formal argument or alternatives.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy