Corpus ID: 225068149

Efficiently Mitigating Classification Bias via Transfer Learning

@article{Jin2020EfficientlyMC,
  title={Efficiently Mitigating Classification Bias via Transfer Learning},
  author={Xisen Jin and Francesco Barbieri and Aida Mostafazadeh Davani and Brendan Kennedy and Leonardo Neves and Xiang Ren},
  journal={ArXiv},
  year={2020},
  volume={abs/2010.12864}
}
Prediction bias in machine learning models refers to unintended model behaviors that discriminate against inputs mentioning or produced by certain groups; for example, hate speech classifiers predict more false positives for neutral text mentioning specific social groups. Mitigating bias for each task or domain is inefficient, as it requires repetitive model training, data annotation (e.g., demographic information), and evaluation. In pursuit of a more accessible solution, we propose the… Expand
1 Citations

Figures and Tables from this paper

References

SHOWING 1-10 OF 43 REFERENCES
Mitigating Unwanted Biases with Adversarial Learning
Measuring and Mitigating Unintended Bias in Text Classification
Explicit Inductive Bias for Transfer Learning with Convolutional Networks
Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations
Adversarially robust transfer learning
Domain-Adversarial Training of Neural Networks
Investigating Gender Bias in BERT
Transfer of Machine Learning Fairness across Domains
Reducing Gender Bias in Abusive Language Detection
...
1
2
3
4
5
...