FairPrep: Promoting Data to a First-Class Citizen in Studies on Fairness-Enhancing Interventions

@inproceedings{Schelter2020FairPrepPD,
  title={FairPrep: Promoting Data to a First-Class Citizen in Studies on Fairness-Enhancing Interventions},
  author={S. Schelter and Yuxuan He and Jatin Khilnani and Julia Stoyanovich},
  booktitle={EDBT},
  year={2020}
}
The importance of incorporating ethics and legal compliance into machine-assisted decision-making is broadly recognized. Further, several lines of recent work have argued that critical opportunities for improving data quality and representativeness, controlling for bias, and allowing humans to oversee and impact computational processes are missed if we do not consider the lifecycle stages upstream from model training and deployment. Yet, very little has been done to date to provide system-level… Expand
13 Citations
Fair Data Integration
  • 1
  • PDF
Teaching Responsible Data Science: Charting New Pedagogical Territory
  • 2
  • PDF
Responsible data management
  • 7
  • PDF
Responsible AI Challenges in End-to-end Machine Learning
  • PDF
Post-Hoc Methods for Debiasing Neural Networks
  • 1
The impact of rewriting on coverage constraint satisfaction
  • PDF
The Many Facets of Data Equity
  • PDF
...
1
2
...

References

SHOWING 1-10 OF 45 REFERENCES
AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias
  • 187
  • Highly Influential
  • PDF
A comparative study of fairness-enhancing interventions in machine learning
  • 195
  • Highly Influential
  • PDF
Fides: Towards a Platform for Responsible Data Science
  • 23
  • PDF
FairTest: Discovering Unwarranted Associations in Data-Driven Applications
  • 76
  • PDF
Interventional Fairness: Causal Database Repair for Algorithmic Fairness
  • 48
  • PDF
Certifying and Removing Disparate Impact
  • 752
  • PDF
Fairness testing: testing software for discrimination
  • 146
  • PDF
Fairness-Aware Programming
  • 17
Measuring discrimination in algorithmic decision making
  • 56
  • PDF
...
1
2
3
4
5
...