# DCAST: Diverse Class-Aware Self-Training Mitigates Selection Bias for Fairer Learning

arXiv: https://arxiv.org/abs/2409.20126 · HTML: https://mlsanity.com/paper/2409.20126/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 42 references that are in the map.
- First posted on arXiv 30 Sep 2024.

## Builds on (most cited first, 6 of 6)

- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [A review of domain adaptation without target labels](https://mlsanity.com/paper/1901.05335/) (2019)
- [Causally Regularized Learning with Agnostic Data Selection Bias](https://mlsanity.com/paper/1708.06656/) (2017)
- [Feature-Level Domain Adaptation](https://mlsanity.com/paper/1512.04829/) (2015)
- [Selection Bias Explorations and Debias Methods for Natural Language Sentence Matching Datasets](https://mlsanity.com/paper/1905.06221/) (2019)
- [Importance Weighted Generative Networks](https://mlsanity.com/paper/1806.02512/) (2018)

## Built on by (most cited first, 2 of 2)

- [From n-gram to Attention: How Model Architectures Learn and Propagate Bias in Language Modeling](https://mlsanity.com/paper/2505.12381/) (2025)
- [Metric-DST: Mitigating Selection Bias Through Diversity-Guided Semi-Supervised Metric Learning](https://mlsanity.com/paper/2411.18442/) (2024)

## Abstract (arXiv)

Fairness in machine learning seeks to mitigate model bias against individuals based on sensitive features such as sex or age, often caused by an uneven representation of the population in the training data due to selection bias. Notably, bias unascribed to sensitive features is challenging to identify and typically goes undiagnosed, despite its prominence in complex high-dimensional data from fields like computer vision and molecular biomedicine. Strategies to mitigate unidentified bias and evaluate mitigation methods are crucially needed, yet remain underexplored. We introduce: (i) Diverse Class-Aware Self-Training (DCAST), model-agnostic mitigation aware of class-specific bias, which promotes sample diversity to counter confirmation bias of conventional self-training while leveraging unlabeled samples for an improved representation of the underlying population; (ii) hierarchy bias, multivariate and class-aware bias induction without prior knowledge. Models learned with DCAST showed improved robustness to hierarchy and other biases across eleven datasets, against conventional self-training and six prominent domain adaptation techniques. Advantage was largest on multi-class classification, emphasizing DCAST as a promising strategy for fairer learning in different contexts.