mlsanityData to 7 Oct 2026

Addressing Fairness, Bias and Class Imbalance in Machine Learning: the FBI-loss

arXiv 2105.06345 ↗First posted 13 May 2021cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Resilience to class imbalance and confounding biases, together with the assurance of fairness guarantees are highly desirable properties of autonomous decision-making systems with real-life impact. Many different targeted solutions have been proposed to address separately these three problems, however a unifying perspective seems to be missing. With this work, we provide a general formalization, showing that they are different expressions of unbalance. Following this intuition, we formulate a unified loss correction to address issues related to Fairness, Biases and Imbalances (FBI-loss). The correction capabilities of the proposed approach are assessed on three real-world benchmarks, each associated to one of the issues under consideration, and on a family of synthetic data in order to better investigate the effectiveness of our loss on tasks with different complexities. The empirical results highlight that the flexible formulation of the FBI-loss leads also to competitive performances with respect to literature solutions specialised for the single problems.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 20 of its 78 references that are in the map. First posted on arXiv 13 May 2021.

Builds on

20 of 78 references.

References · 20

  1. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  2. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  3. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  4. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  5. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  6. 2017Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraintscited by 420
  7. 2017Right for the Right Reasons: Training Differentiable Models by Constraining their Explanationscited by 293
  8. 2018Learning Not to Learn: Training Deep Neural Networks with Biased Datacited by 255
  9. 2019Causality matters in medical imagingcited by 193
  10. 2017Controllable Invariance through Adversarial Feature Learningcited by 127
  11. 2018Invariant Representations without Adversarial Trainingcited by 111
  12. 2017Deep Over-sampling Framework for Classifying Imbalanced Datacited by 58
8 more
  1. 2018Two-Player Games for Efficient Non-Convex Constrained Optimizationcited by 55
  2. 2013Scalable Object Detection using Deep Neural Networkscited by 30
  3. 2019Machine learning in policy evaluation: new tools for causal inferencecited by 10
  4. 2019Representation Learning with Statistical Independence to Mitigate Biascited by 6
  5. 2020Convolutional Neural Networks based Focal Loss for Class Imbalance Problem: A Case Study of Canine Red Blood Cells Morphology Classificationcited by 6
  6. 2020Transfer learning with class-weighted and focal loss function for automatic skin cancer classificationcited by 5
  7. 2019Measuring the effects of confounders in medical supervised classification problems: the Confounding Index (CI)cited by 3
  8. 2018Focal Loss Dense Detector for Vehicle Surveillancecited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 1; 2024: 2; 2025: 0; 2026: 1.

6 papers.

  1. 2022Towards A Holistic View of Bias in Machine Learning: Bridging Algorithmic Fairness and Imbalanced Learningcited by 10
  2. 2022Improved Input Reprogramming for GAN Conditioningcited by 7
  3. 2024Properties of fairness measures in the context of varying class imbalance and protected group ratioscited by 7
  4. 2023Fair Oversampling Technique using Heterogeneous Clusterscited by 5
  5. 2024Validity of Feature Importance in Low-Performing Machine Learning for Tabular Biomedical Datacited by 0
  6. 2026Multi-Level Analyzation of Imbalance to Resolve Non-IID-Ness in Federated Learningcited by 0