mlsanityData to 7 Oct 2026

Modeling Implicit Bias with Fuzzy Cognitive Maps

arXiv 2112.12713 ↗First posted 23 Dec 2021cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

This paper presents a Fuzzy Cognitive Map model to quantify implicit bias in structured datasets where features can be numeric or discrete. In our proposal, problem features are mapped to neural concepts that are initially activated by experts when running what-if simulations, whereas weights connecting the neural concepts represent absolute correlation/association patterns between features. In addition, we introduce a new reasoning mechanism equipped with a normalization-like transfer function that prevents neurons from saturating. Another advantage of this new reasoning mechanism is that it can easily be controlled by regulating nonlinearity when updating neurons' activation values in each iteration. Finally, we study the convergence of our model and derive analytical conditions concerning the existence and unicity of fixed-point attractors.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 12 of its 43 references that are in the map. First posted on arXiv 23 Dec 2021.

Builds on

12 of 43 references.

References · 12

  1. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  2. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  3. 2014Certifying and removing disparate impactcited by 715
  4. 2018AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Biascited by 319
  5. 2018A comparative study of fairness-enhancing interventions in machine learningcited by 208
  6. 2018Path-Specific Counterfactual Fairnesscited by 179
  7. 2020Survey on Causal-based Machine Learning Fairness Notionscited by 53
  8. 2016Auditing Black-box Models for Indirect Influencecited by 41
  9. 2015Exposing the Probabilistic Causal Structure of Discriminationcited by 5
  10. 2021A fuzzy-rough uncertainty measure to discover bias encoded explicitly or implicitly in features of structured pattern classification datasetscited by 5
  11. 2021Recurrence-Aware Long-Term Cognitive Network for Explainable Pattern Classificationcited by 4
  12. 2020Ethical Adversaries: Towards Mitigating Unfairness with Adversarial Machine Learningcited by 3

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1.

2 papers.

  1. 2023Measuring Implicit Bias Using SHAP Feature Importance and Fuzzy Cognitive Mapscited by 0
  2. 2024On the Convergence of Sigmoid and tanh Fuzzy General Grey Cognitive Mapscited by 0