Research map / Probabilistic and scientific modeling / Causal discovery
Avoiding Discrimination through Causal Reasoning
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 |
|---|---|---|---|
| Use causal graphs and resolving variables instead of only observational fairness criteria | Bayes-optimal unconstrained and equal-odds predictors · Causal discrimination analysis | identifiability of unresolved discrimination | Helped |
| Require the predictor distribution to be invariant under interventions on proxy P | Predictors using proxy P · Causal proxy discrimination | proxy discrimination | Helped |
| Adjust the predictor to cancel P's additive linear influence | Linear structural equation models · Causal proxy discrimination | proxy discrimination | Helped |
| Use unawareness when there is no directed path from a proxy to the features | Predictors based on features X · Causal proxy discrimination | proxy discrimination | Helped |
| Exclude features affected by A without a resolving variable | Predictors constructed from features · Unresolved discrimination | unresolved discrimination | Helped |
| Remove proxy effects using observational conditional adjustment instead of interventional adjustment | Predictors based on adjusted features · Causal proxy discrimination | proxy discrimination | Hurt |
| Give the predictor access to A so it can cancel A's unresolved influence while retaining resolved paths | Predictors avoiding unresolved discrimination · Linear structural equation example | retention of resolved influence | Helped |
| Avoid unresolved discrimination without giving the predictor access to A | Predictors using resolving variable E and feature X · Linear structural equation example | retention of resolved influence | Hurt |
Closest papers by meaning
- Reconciling Predictive and Statistical Parity: A Causal Approach (AAAI 2024 · similarity 0.92)
- Causal Bias Detection in Generative Artifical Intelligence (NeurIPS 2026 · similarity 0.90)
- FairPFN: A Tabular Foundation Model for Causal Fairness (ICML 2025 · similarity 0.90)
- Interventional Fairness on Partially Known Causal Graphs: A Constrained Optimization Approach (ICLR 2024 · similarity 0.90)
- Causal Fairness under Unobserved Confounding: A Neural Sensitivity Framework (ICLR 2024 · similarity 0.89)
- Fairness-Accuracy Trade-Offs: A Causal Perspective (AAAI 2025 · similarity 0.89)
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.