Research map / Probabilistic and scientific modeling / Causal discovery
Causal approaches to fairness
Apply causal graphs and interventional criteria to define and enforce fairness.
46 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2017–2026) · an approach in Causal discovery, keyword cluster “counterfactual · causal inference · causal representation”
State History Tried Preprints Who Export
Where it stands
Not enough benchmark data Fewer than four papers report the same benchmark, so there is no record to follow.
14 papers in 2023–24 and 15 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic shrank, from 6.0% to 4.5%.
How this is decided
A benchmark is tracked when at least four papers of this approach report their own method on the same dataset and metric in at least two different years. Its record is the best number reported up to 2024 compared with the best reported in 2025–26: still improving means at least 1% better, flat means at most 0.2% better with at least two papers from 2025–26 trying. Numbers on a different scale from the rest (a fraction among percentages) and far outliers are left out. Results come from different papers with different setups, so they are signals, not head-to-head comparisons. The share of papers is counted at ICML, NeurIPS, ICLR, CVPR and AAAI.
How it got here
Most cited paper of each year
- 2017 · Avoiding Discrimination through Causal Reasoning (NeurIPS 2017 · 176 citations)
- 2018 · Fair Inference on Outcomes (AAAI 2018 · 229 citations)
- 2020 · Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect (NeurIPS 2020 · 50 citations)
- 2021 · Counterfactual Fairness with Disentangled Causal Effect Variational Autoencoder (AAAI 2021 · 40 citations)
- 2022 · Training a Resilient Q-network against Observational Interference (AAAI 2022 · 14 citations)
- 2023 · Context De-Confounded Emotion Recognition (CVPR 2023 · 65 citations)
- 2024 · Robust Emotion Recognition in Context Debiasing (CVPR 2024 · 29 citations)
- 2025 · Unveiling Environmental Sensitivity of Individual Gains in Influence Maximization (NeurIPS 2025 · 2 citations)
- 2026 · Uncovering Bias Paths with LLM-guided Causal Discovery: An Active Learning and Dynamic Scoring Approach (AAAI 2026 · 2 citations)
Earliest papers here
- Avoiding Discrimination through Causal Reasoning (NeurIPS 2017 · 176 citations)
- Fair Inference on Outcomes (AAAI 2018 · 229 citations)
- Equality of Opportunity in Classification: A Causal Approach (NeurIPS 2018 · 32 citations)
What has been tried
37 papers here report 303 measured changes (a component added, removed or swapped, compared with a baseline): helped 63%, no clear effect 8%, hurt 22%, mixed 7%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| Remove the vanilla CAER model | EMOTIC and CAER-S · mAP / accuracy | 32.51 -> 19.64; 88.41 -> 62.87 | Hurt | Robust Emotion Recognition in Context Debiasing (CVPR 2024 · 29 citations) |
| Increase ITE noise up to the reported robust range | GoodReads · sum of ITE stability | No clear effect | Unveiling Environmental Sensitivity of Individual Gains in Influence Maximization (NeurIPS 2025 · 2 citations) | |
| Increase dataset size | Synthetic causal case studies · prediction ATE | Helped | FairPFN: A Tabular Foundation Model for Causal Fairness (ICML 2025 · 0 citations) | |
| Replace linear features with spline features | Action Sparsity Dataset · Label accuracy | 0.77 { ± 0.03} -> 0.72 { ± 0.03} (n=20); 0.84 { ± 0.01} -> 0.86 { ± 0.01} (n=10000) | Mixed | Sample-efficient Learning of Concepts with Theoretical Guarantees: from Data to Concepts without Interventions (NeurIPS 2025 · 0 citations) |
| Algorithm with structural conditions (proposed) vs. base model without structural conditions for identifying dependencies on synthetic linear Gaussian data | Synthetic data, 8 to 20 observed variables · precision and recall of first-order direct relations | Helped | Detecting and Identifying Selection Structure in Sequential Data (ICML 2024 · 0 citations) |
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 29 papers; from OpenAlex and the papers' affiliations).
- Carnegie Mellon University · 4 papers
- Max Planck Institute for Intelligent Systems · 3 papers
- Jilin Provincial Key Laboratory of Intelligence Science and Engineering · 2 papers
- Engineering Research Center of AI and Robotics · 2 papers
- Academy for Engineering and Technology · 2 papers
- Google · 2 papers
- ELLIS Institute Tübingen · 2 papers
- University of Michigan - Ann Arbor · 2 papers
- Korteweg-de Vries Institute · 2 papers
Use it
Download BibTeX of 38 key papersOpen the topic in the interactive map
Get alerts. Describe your idea in scime atlas and save it (free scime account): you get a weekly email when new preprints land close to it.
Related approaches
Same keyword cluster
- Latent-variable causal estimation (117 papers)
- Causal effect identification (107 papers)
- Causal representation identifiability (122 papers)
- Counterfactual identification and bounds (92 papers)
Elsewhere in the topic
- Constraint-based structure learning with latents (90 papers)
- Identifiability with hidden confounders (85 papers)
- Interventional causal discovery (68 papers)
- Differentiable and score-based DAG learning (52 papers)
- Causal discovery from time series (51 papers)
Benchmark numbers, ablations and baseline numbers are extracted by AI from each paper's full text and can be wrong; the paper is the authority. Data: results index of 2026-11-02, citation counts from OpenAlex (2026-10-09).