Research map / Learning theory and algorithms / Fairness
Inherent Tradeoffs in Learning Fair Representations
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| increase adversarial loss coefficient from 0 (NoDebias) to 50.0 (ablation) | MLP with adversarial debiasing · UCI Adult test (gender sensitive) | demographic parity gap: 0.189 -> 0.028 | Helped |
| increase adversarial loss coefficient from 0 (NoDebias) to 50.0 (ablation) | MLP with adversarial debiasing · UCI Adult test (gender sensitive) | joint error Err_D0 + Err_D1: 0.275 -> 0.360 | Hurt |
| increase adversarial loss coefficient from 0 (NoDebias) to 50.0 (ablation) | MLP with adversarial debiasing · UCI Adult test (gender sensitive) | overall error: 0.157 -> 0.201 | Hurt |
| increase adversarial loss coefficient from 0 (NoDebias) to 50.0 (ablation) | MLP with adversarial debiasing · UCI Adult test (gender sensitive) | accuracy parity gap: 0.115 -> 0.112 | Mixed |
| small adversarial coefficient 0.1 (ablation) | MLP with adversarial debiasing · UCI Adult test (gender sensitive) | demographic parity gap: 0.189 -> 0.190 | No clear effect |
Closest papers by meaning
- Utility-Fairness Trade-Offs and How to Find Them (CVPR 2024 · similarity 0.90)
- Fair Representation Learning with Controllable High Confidence Guarantees via Adversarial Inference (NeurIPS 2025 · similarity 0.89)
- Understanding Fairness and Prediction Error through Subspace Decomposition and Influence Analysis (NeurIPS 2025 · similarity 0.89)
- Fairness without Harm: An Influence-Guided Active Sampling Approach (NeurIPS 2024 · similarity 0.89)
- Fairness without Demographics through Shared Latent Space-Based Debiasing (AAAI 2024 · similarity 0.88)
- Fairness-Accuracy Trade-Offs: A Causal Perspective (AAAI 2025 · similarity 0.88)
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.