mlsanityData to 14 Oct 2026

Multi-group Learning for Hierarchical Groups

arXiv 2402.00258 ↗First posted 1 Feb 2024cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

The multi-group learning model formalizes the learning scenario in which a single predictor must generalize well on multiple, possibly overlapping subgroups of interest. We extend the study of multi-group learning to the natural case where the groups are hierarchically structured. We design an algorithm for this setting that outputs an interpretable and deterministic decision tree predictor with near-optimal sample complexity. We then conduct an empirical evaluation of our algorithm and find that it achieves attractive generalization properties on real datasets with hierarchical group structure.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 30 of its 43 references that are in the map. First posted on arXiv 1 Feb 2024.

Builds on

30 of 43 references.

References · 30

  1. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  2. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  3. 2016Equality of Opportunity in Supervised Learningcited by 2,007
  4. 2021Retiring Adult: New Datasets for Fair Machine Learningcited by 449
  5. 2019Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classificationcited by 404
  6. 2017Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairnesscited by 384
  7. 2018Improving fairness in machine learning systems: What do industry practitioners need?cited by 262
  8. 2020Fairness without Demographics through Adversarially Reweighted Learningcited by 251
  9. 2018Multiaccuracy: Black-Box Post-Processing for Fairness in Classificationcited by 222
  10. 2019Hidden Stratification Causes Clinically Meaningful Failures in Machine Learning for Medical Imagingcited by 216
  11. 2020No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problemscited by 209
  12. 2022Domino: Discovering Systematic Errors with Cross-Modal Embeddingscited by 156
18 more
  1. 2019Does Object Recognition Work for Everyone?cited by 151
  2. 2020Outcome Indistinguishabilitycited by 75
  3. 2018Automated Data Slicing for Model Validation:A Big data - AI Integration Approachcited by 70
  4. 2021Multi-group Agnostic PAC Learnabilitycited by 44
  5. 2022On-Demand Sampling: Learning Optimally from Multiple Distributionscited by 39
  6. 2023Multicalibration as Boosting for Regressioncited by 33
  7. 2019(De)Constructing Bias on Skin Lesion Datasetscited by 30
  8. 2019Advancing subgroup fairness via sleeping expertscited by 30
  9. 2021Simple and near-optimal algorithms for hidden stratification and multi-group learningcited by 28
  10. 2020Bootleg: Chasing the Tail with Self-Supervised Named Entity Disambiguationcited by 24
  11. 2022An Algorithmic Framework for Bias Bountiescited by 21
  12. 2023Identification of Negative Transfers in Multitask Learning Using Surrogate Modelscited by 20
  13. 2022Subgroup Robustness Grows On Trees: An Empirical Baseline Investigationcited by 17
  14. 2021Cross-Domain Data Integration for Named Entity Disambiguation in Biomedical Textcited by 15
  15. 2019An adaptive nearest neighbor rule for classificationcited by 13
  16. 2021A comparison of approaches to improve worst-case predictive model performance over patient subpopulationscited by 12
  17. 2017Gender-From-Iris or Gender-From-Mascara?cited by 9
  18. 2023Agnostic Multi-Group Active Learningcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 2; 2026: 5.

8 papers.

  1. 2025Sample-Efficient Omniprediction for Proper Lossescited by 5
  2. 2025Panprediction: Optimal Predictions for Any Downstream Task and Losscited by 4
  3. 2026Efficient Estimation of Kernel Surrogate Models for Task Attributioncited by 4
  4. 2026Group-realizable multi-group learning by minimizing empirical riskcited by 3
  5. 2024Learning Tree-Structured Composition of Data Augmentationcited by 1
  6. 2026ShakyPrepend: A Multi-Group Learner with Improved Sample Complexitycited by 0
  7. 2026A One-Inclusion Graph Approach to Multi-Group Learningcited by 0
  8. 2026Sample-Optimal Multi-Group Learning with an ERM Oraclecited by 0