mlsanityData to 7 Oct 2026

The Fairness Stitch: Unveiling the Potential of Model Stitching in Neural Network De-Biasing

arXiv 2311.03532 ↗First posted 6 Nov 2023cs.LG cs.IT math.ITcited by 0

Not on the map. Why?

Abstract (arXiv)

The pursuit of fairness in machine learning models has emerged as a critical research challenge in different applications ranging from bank loan approval to face detection. Despite the widespread adoption of artificial intelligence algorithms across various domains, concerns persist regarding the presence of biases and discrimination within these models. To address this pressing issue, this study introduces a novel method called "The Fairness Stitch (TFS)" to enhance fairness in deep learning models. This method combines model stitching and training jointly, while incorporating fairness constraints. In this research, we assess the effectiveness of our proposed method by conducting a comprehensive evaluation of two well-known datasets, CelebA and UTKFace. We systematically compare the performance of our approach with the existing baseline method. Our findings reveal a notable improvement in achieving a balanced trade-off between fairness and performance, highlighting the promising potential of our method to address bias-related challenges and foster equitable outcomes in machine learning models. This paper poses a challenge to the conventional wisdom of the effectiveness of the last layer in deep learning models for de-biasing.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 20 of its 33 references that are in the map. First posted on arXiv 6 Nov 2023.

Builds on

20 of 33 references.

References · 20

  1. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  2. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  3. 2022Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distributioncited by 722
  4. 2017Opening the Black Box of Deep Neural Networks via Informationcited by 494
  5. 2017Age Progression/Regression by Conditional Adversarial Autoencodercited by 426
  6. 2017Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairnesscited by 381
  7. 2022Last Layer Re-Training is Sufficient for Robustness to Spurious Correlationscited by 379
  8. 2020Fairness in Machine Learning: A Surveycited by 369
  9. 2018Fairness Without Demographics in Repeated Loss Minimizationcited by 363
  10. 2020Fairness without Demographics through Adversarially Reweighted Learningcited by 251
  11. 2014Understanding image representations by measuring their equivariance and equivalencecited by 240
  12. 2022Surgical Fine-Tuning Improves Adaptation to Distribution Shiftscited by 205
8 more
  1. 2021Revisiting Model Stitching to Compare Neural Representationscited by 203
  2. 2015Censoring Representations with an Adversarycited by 191
  3. 2019Fairness in Recommendation Ranking through Pairwise Comparisonscited by 127
  4. 2019Putting Fairness Principles into Practice: Challenges, Metrics, and Improvementscited by 70
  5. 2018FNNC: Achieving Fairness through Neural Networkscited by 43
  6. 2021Technical Challenges for Training Fair Neural Networkscited by 20
  7. 2023Last-Layer Fairness Fine-tuning is Simple and Effective for Neural Networkscited by 17
  8. 2020README: REpresentation learning by fairness-Aware Disentangling MEthodcited by 10

Built on by

Not cited yet.