Research map / Learning theory and algorithms
Fairness: research map
550 papers on Fairness in Learning theory and algorithms, from ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR (2016–2026), grouped into 2 clusters and 7 approaches. The busiest year so far is 2024.
What it is
Making automated decisions fair across groups of people: defining fairness, measuring it, and training or adjusting models to satisfy it, in classification, ranking, recommendation and allocation.
Terms you will see on this page:
- Demographic parity
- equal positive-decision rates across groups.
- Equalized odds
- equal error rates across groups.
- Post-processing
- adjusting a trained model's outputs to meet a fairness criterion.
Start reading with the most cited papers here:
- Counterfactual Fairness (NeurIPS 2017 · 842 citations)
- Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness (ICML 2018 · 383 citations)
Within Learning theory and algorithms, its share shrank from 7.5% in 2023–24 to 5.8% in 2025–26 (167 → 140 papers at ICML, NeurIPS, ICLR, CVPR and AAAI, the venues with data for all four years).
Explore Fairness in the interactive map
Working on something in this topic? Describe your idea in scime atlas to see which approach it falls under, the closest papers by meaning and how crowded the spot has become.
What changed recently
Approaches whose share of the topic moved most between 2023–24 and 2025–26 (ICML, NeurIPS, ICLR, CVPR and AAAI):
- Fairness-constrained classification rising: 16% → 31% of the topic (27 → 44 papers)
- Minimax fairness via sampling rising: 6% → 9% of the topic (10 → 12 papers)
- Post-processing and transport for fairness falling: 26% → 16% of the topic (43 → 23 papers)
- Causal and policy fairness in decisions falling: 19% → 12% of the topic (31 → 17 papers)
Papers from 2025–2026 that are already cited most:
- Fairness-Accuracy Trade-Offs: A Causal Perspective (AAAI 2025 · 11 citations)
Approaches and key papers
Fair classification · 385 papers
Keywords: fair, classifier, classification
Approaches in this cluster:
- Fairness-constrained classification (164 papers)
Learn classifiers under group or individual fairness constraints, with guarantees on fairness and accuracy. - Post-processing and transport for fairness (111 papers)
Adjust or transform classifiers, often via optimal transport, to remove discrimination while preserving utility. - Fair allocation and selection (71 papers)
Design fair rankings, resource allocation and subset selection algorithms with provable fairness guarantees. - Minimax fairness via sampling (39 papers)
Reach group fairness by reweighting or actively sampling data, including without demographic labels.
Most cited and most cited since 2024:
- Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness (ICML 2018 · 383 citations)
- On Fairness and Calibration (NeurIPS 2017 · 279 citations)
- Arbitrariness and Social Prediction: The Confounding Role of Variance in Fair Classification (AAAI 2024 · 18 citations)
- A Sequentially Fair Mechanism for Multiple Sensitive Attributes (AAAI 2024 · 9 citations)
Fair decision-making · 165 papers
Keywords: decision, making, systems
Approaches in this cluster:
- Causal and policy fairness in decisions (78 papers)
Frames fairness in decision-making through causal analysis, preference-based notions and optimal fair policies. - Fairness auditing and regularization (67 papers)
Audits and mitigates unfairness with sensitivity analysis, data influence and differentiable regularizers. - Fairness in recommendation and ranking (20 papers)
Defines fairness objectives for users and items in recommender systems and rankings.
Most cited and most cited since 2024:
- Counterfactual Fairness (NeurIPS 2017 · 842 citations)
- Delayed Impact of Fair Machine Learning (ICML 2018 · 163 citations)
- Fairness-Accuracy Trade-Offs: A Causal Perspective (AAAI 2025 · 11 citations)
- Intra- and Inter-group Optimal Transport for User-Oriented Fairness in Recommender Systems (AAAI 2024 · 8 citations)
Related topics in Learning theory and algorithms
- Matrix and tensor methods (1,467)
- Sample complexity (1,553)
- Combinatorial and search optimization (1,576)
- Submodular and game algorithms (1,064)
- Prediction and decision losses (2,400)
- Kernels and regression theory (1,272)
- Clustering (998)
- Optimal transport (462)
