Ethical Machine Learning
Injecting Ethical and Legal Constraints into Machine Learning Models
Equipping ML models with ethical and legal constraints is a serious issue as without this the future of ML is at risk. In the UK, this is recognized by the House of Commons Science and Technology Committee, which has formed a Council of Data Ethics.
Building ML models with fairness, confidentiality, and transparency constraints is an active research area, and disjoint frameworks are available for addressing each constraint. However, how to put them all together is not obvious. Our long-term goal is to develop an ML framework with plug-and-play constraints that is able to handle any of the mentioned constraints, their combinations, and also new constraints that might be stipulated in the future.
- Novi Quadrianto
- Thomas Kehrenberg (PhD Student 2017–present)
- Oliver Thomas (PhD Student 2017–present)
- Zexun Chen (Postdoc 2017-2018)
- Thomas Kehrenberg, Zexun Chen and Novi Quadrianto. Tuning Fairness by Balancing Target Labels. Frontiers in Artificial Intelligence, 2020.
- Artyom Gadetsky, Kirill Struminsky, Christopher Robinson, Novi Quadrianto and Dmitry Vetrov. Low-variance black-box gradient estimates for the Plackett-Luce distribution. Thirty-Fourth AAAI Conference on Artificial Intelligence AAAI, 2020.
- Novi Quadrianto, Viktoriia Sharmanska and Oliver Thomas. Discovering Fair Representations in the Data Domain. IEEE Conference on Computer Vision and Pattern Recognition CVPR, 2019.
- Bradley Butcher, Vincent S Huang, Jeremy Reffin, Sema K Sgaier, Grace Charles, Novi Quadrianto. Causal datasheet - An approximate guide to practically assess Bayesian networks in the real world. NeurIPS workshop on machine learning and causal inference for improved decision making, 2019.
- Novi Quadrianto and Viktoriia Sharmanska. Recycling Privileged Learning and Distribution Matching for Fairness. Neural Information Processing Systems NIPS, 2017.