Research map / Learning theory and algorithms / Fairness
Counterfactually Fair Representation
Zhiqun Zuo, Mohammad Mahdi Khalili, Xueru Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| use counterfactually fair representation instead of CE (non-descendants only) | CE · Synthetic data | MSE (L): 0.7868 -> 0.4739 | Improved |
| use counterfactually fair representation instead of CR regularization | CR · Synthetic data | TE: 0.2572 -> 0.000 | Improved |
| use counterfactually fair representation instead of unfair full-feature model | UF · Synthetic data | TE: 1.2499 -> 0.000 | Improved |
| use fair representation instead of CA (average counterfactual augmentation) | CA · Synthetic data | MSE (L): 0.3467 -> 0.4739 | Hurt |
| use fair representation instead of CR | CR · Law School CVAE | TE (G): 0.1035 -> 0.0663 | Improved |
| use fair representation instead of CR | CR · Law School CVAE | TE (L): 0.0880 -> 0.0655 | Improved |
| use fair representation instead of CR | CR · Law School DCEVAE | TE (G): 0.0463 -> 0.0693 | Hurt |
| use fair representation instead of CR | CR · Law School DCEVAE | TE (L): 0.0821 -> 0.0968 | Hurt |
| use fair representation instead of ICA | ICA · Law School CVAE | TE (G): 0.1633 -> 0.0663 | Improved |
| use fair representation instead of CE | CE · Law School CVAE | MSE (G): 0.8900 -> 0.8689 | Improved |
| use fair representation instead of CE | CE · Law School DCEVAE | MSE (G): 0.8781 -> 0.8679 | Improved |
| use fair representation instead of unfair UF baseline | UF · Law School CVAE | MSE (G): 0.8664 -> 0.8689 | No clear effect |
Closest papers by meaning
- Counterfactual Fairness by Combining Factual and Counterfactual Predictions (NeurIPS 2024 · similarity 0.90)
- Towards counterfactual fairness through auxiliary variables (ICLR 2025 · similarity 0.88)
- Interventional Fairness on Partially Known Causal Graphs: A Constrained Optimization Approach (ICLR 2024 · similarity 0.87)
- Fairness on Principal Stratum: A New Perspective on Counterfactual Fairness (ICML 2025 · similarity 0.86)
- FairPFN: A Tabular Foundation Model for Causal Fairness (ICML 2025 · similarity 0.86)
- Towards Harmless Rawlsian Fairness Regardless of Demographic Prior (NeurIPS 2024 · similarity 0.86)
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.
