Distributionally Robust Data Join
Not on the map. Why?
Abstract (arXiv)
Suppose we are given two datasets: a labeled dataset and unlabeled dataset which also has additional auxiliary features not present in the first dataset. What is the most principled way to use these datasets together to construct a predictor? The answer should depend upon whether these datasets are generated by the same or different distributions over their mutual feature sets, and how similar the test distribution will be to either of those distributions. In many applications, the two datasets will likely follow different distributions, but both may be close to the test distribution. We introduce the problem of building a predictor which minimizes the maximum loss over all probability distributions over the original features, auxiliary features, and binary labels, whose Wasserstein distance is r1 away from the empirical distribution over the labeled dataset and r2 away from that of the unlabeled dataset. This can be thought of as a generalization of distributionally robust optimization (DRO), which allows for two data sources, one of which is unlabeled and may contain auxiliary features.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 15 of its 47 references that are in the map. First posted on arXiv 11 Feb 2022.
Builds on
15 of 47 references.
References · 15
- 2018A Reductions Approach to Fair Classificationcited by 585
- 2017Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairnesscited by 381
- 2018Fairness Without Demographics in Repeated Loss Minimizationcited by 363
- 2018Learning Models with Uniform Performance via Distributionally Robust Optimizationcited by 334
- 2015Data-driven Distributionally Robust Optimization Using the Wasserstein Metric: Performance Guarantees and Tractable Reformulationscited by 285
- 2018Multiaccuracy: Black-Box Post-Processing for Fairness in Classificationcited by 221
- 2019Wasserstein Distributionally Robust Optimization: Theory and Applications in Machine Learningcited by 169
- 2015Distributionally Robust Logistic Regressioncited by 124
- 2019Assessing Algorithmic Fairness with Unobserved Protected Class Using Data Combinationcited by 79
- 2020A Distributionally Robust Approach to Fair Classificationcited by 43
- 2021Evaluating Fairness of Machine Learning Models Under Uncertain and Incomplete Informationcited by 33
- 2021Fairness without Imputation: A Decision Tree Approach for Fair Prediction with Missing Valuescited by 24
3 more
- 2021Fair Classification with Adversarial Perturbationscited by 23
- 2020Minimax Group Fairness: Algorithms and Experimentscited by 17
- 2021Multiaccurate Proxies for Downstream Fairnesscited by 17
Built on by
Citing papers per year: 2024: 2.
2 papers.