A Fair Classifier Embracing Triplet Collapse
Not on the map. Why?
Abstract (arXiv)
In this paper, we study the behaviour of the triplet loss and show that it can be exploited to limit the biases created and perpetuated by machine learning models. Our fair classifier uses the collapse of the triplet loss when its margin is greater than the maximum distance between two points in the latent space, in the case of stochastic triplet selection.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 14 of its 26 references that are in the map. First posted on arXiv 7 Jun 2023.
Builds on
14 of 26 references.
References · 14
- 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
- 2016Equality of Opportunity in Supervised Learningcited by 2,000
- 2017Counterfactual Fairnesscited by 802
- 2017In Defense of the Triplet Loss for Person Re-Identificationcited by 784
- 2014Certifying and removing disparate impactcited by 715
- 2017NormFace: L2 Hypersphere Embedding for Face Verificationcited by 237
- 2015The Variational Fair Autoencodercited by 223
- 2018A comparative study of fairness-enhancing interventions in machine learningcited by 208
- 2019Flexibly Fair Representation Learning by Disentanglementcited by 196
- 2020Fairness in Machine Learningcited by 194
- 2019On the Fairness of Disentangled Representationscited by 144
- 2019Metric Learning for Individual Fairnesscited by 51
2 more
- 2021Fair Normalizing Flowscited by 38
- 2021Contrastive Learning for Fair Representationscited by 34
Built on by
Not cited yet.