Equality of Opportunity in Supervised Learning
Explore this paper's citation graph
Summary
This work proposes a criterion for discrimination against a specified sensitive attribute in supervised learning, where the goal is to predict some target based on available features and shows how to optimally adjust any learned predictor so as to remove discrimination according to this definition.
- Type
- preprint
- Published
- 2016-10-07
- Cited by
- 5,364
- References
- 16
- Access
- Open access
- OpenAlex
- https://openalex.org/W2530395818
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:7567061
Keywords
Computer science, Interpretation (philosophy), Disadvantaged, Machine learning, Artificial intelligence
References
- Learning Fair Classifiers
- All of Statistics: A Concise Course in Statistical Inference
- Big Data's Disparate Impact
- Certifying and Removing Disparate Impact
- Discrimination-aware data mining
- Fairness through awareness
- Building Classifiers with Independency Constraints
- Credit Scoring and Its Effects on the Availability and Affordability of Credit
- Learning Fair Representations
- A multidisciplinary survey on discrimination analysis
- On the relation between accuracy and fairness in binary classification
- Inherent Trade-Offs in the Fair Determination of Risk Scores
- The Variational Fair Autoencoder
- Big Data�s Disparate Impact
Cited by
- An Empirical Characterization of Fair Machine Learning For Clinical Risk Prediction
- Removing the influence of group variables in high-dimensional predictive modelling
- The Crossover Process: Learnability meets Protection from Inference Attacks
- Satisfying Real-world Goals with Dataset Constraints
- Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment
- Rawlsian Fairness for Machine Learning
- Fair Prediction with Disparate Impact: A Study of Bias in Recidivism Prediction Instruments
- Achieving Non-Discrimination in Data Release
- Fair Learning in Markovian Environments
- Algorithmic Decision Making and the Cost of Fairness
- Quantifying Program Bias
- Achieving non-discrimination in prediction
- A Roadmap for a Rigorous Science of Interpretability
- Fairness in Reinforcement Learning
- Towards A Rigorous Science of Interpretable Machine Learning
- Measuring discrimination in algorithmic decision making
- Fairness in Criminal Justice Risk Assessments: The State of the Art
- An algorithm for removing sensitive information: Application to race-independent recidivism prediction
- A Short Review of Ethical Challenges in Clinical Natural Language Processing
- Auditing Search Engines for Differential Satisfaction Across Demographics
Related papers
- Starting unequal: How’s life for disadvantaged children?
- A Very Important Question for Establishing a Harmonious Society——How to treat the disadvantaged groups
- Selection of advantaged and disadvantaged South African students- for university admission
- Teaching Reading and Literature to the Disadvantaged.
- On Assistant Countermeasures for Bi Disadvantaged Students in Colleges
- Particularity of Disadvantaged Groups in China
- The Practice of and Consideration about Public Library's Service for The Disadvantaged Groups
- New Dimensions of Educational Programs For Disadvantaged Youth
- Stay a Little Longer? Teacher Turnover, Retention and Quality in Disadvantaged Schools