mlsanityData to 14 Oct 2026

FairGRAPE: Fairness-aware GRAdient Pruning mEthod for Face Attribute Classification

arXiv 2207.10888 ↗First posted 22 Jul 2022cs.CV cs.AI cs.LGcited by 30

Not on the map. Why?

Abstract (arXiv)

Existing pruning techniques preserve deep neural networks' overall ability to make correct predictions but may also amplify hidden biases during the compression process. We propose a novel pruning method, Fairness-aware GRAdient Pruning mEthod (FairGRAPE), that minimizes the disproportionate impacts of pruning on different sub-groups. Our method calculates the per-group importance of each model weight and selects a subset of weights that maintain the relative between-group total importance in pruning. The proposed method then prunes network edges with small importance values and repeats the procedure by updating importance values. We demonstrate the effectiveness of our method on four different datasets, FairFace, UTKFace, CelebA, and ImageNet, for the tasks of face attribute classification where our method reduces the disparity in performance degradation by up to 90% compared to the state-of-the-art pruning algorithms. Our method is substantially more effective in a setting with a high pruning rate (99%). The code and dataset used in the experiments are available at https://github.com/Bernardo1998/FairGRAPE

Key facts. Cited by 30 papers in the map (data through 14 Oct 2026). Builds on 51 of its 64 references that are in the map. First posted on arXiv 22 Jul 2022.

Builds on

51 of 64 references.

References · 51

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  3. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  4. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  5. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
  6. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,262
  7. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 2,031
  8. 2016Pruning Filters for Efficient ConvNetscited by 1,143
  9. 2018SNIP: Single-shot Network Pruning based on Connection Sensitivitycited by 812
  10. 2017Channel Pruning for Accelerating Very Deep Neural Networkscited by 702
  11. 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 676
  12. 2020What is the State of Neural Network Pruning?cited by 583
38 more
  1. 2019Importance Estimation for Neural Network Pruningcited by 541
  2. 2020Picking Winning Tickets Before Training by Preserving Gradient Flowcited by 471
  3. 2017Age Progression/Regression by Conditional Adversarial Autoencodercited by 429
  4. 2017Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraintscited by 420
  5. 2017A Survey of Model Compression and Acceleration for Deep Neural Networkscited by 301
  6. 2019Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigationcited by 252
  7. 2017NISP: Pruning Networks using Neuron Importance Score Propagationcited by 228
  8. 2019Learning De-biased Representations with Biased Representationscited by 199
  9. 2019What Do Compressed Deep Neural Networks Forget?cited by 171
  10. 2020Characterising Bias in Compressed Modelscited by 167
  11. 2019Drawing Early-Bird Tickets: Towards More Efficient Training of Deep Networkscited by 160
  12. 2019REPAIR: Removing Representation Bias by Dataset Resamplingcited by 157
  13. 2019Towards Fairer Datasets: Filtering and Balancing the Distribution of the People Subtree in the ImageNet Hierarchycited by 156
  14. 2018Synthetic Data Augmentation using GAN for Improved Liver Lesion Classificationcited by 136
  15. 2020Fair Attribute Classification through Latent Space De-biasingcited by 125
  16. 2019Fairness in Deep Learning: A Computational Perspectivecited by 123
  17. 2018Deep Learning in Mobile and Wireless Networking: A Surveycited by 118
  18. 2021Learning Debiased Representation via Disentangled Feature Augmentationcited by 116
  19. 2018Turning a Blind Eye: Explicit Removal of Biases and Variation from Deep Neural Network Embeddingscited by 114
  20. 2021Understanding and Evaluating Racial Biases in Image Captioningcited by 108
  21. 2015Convolutional neural networks with low-rank regularizationcited by 103
  22. 2021Towards Measuring Fairness in AI: the Casual Conversations Datasetcited by 80
  23. 2019Guarantees for Spectral Clustering with Fairness Constraintscited by 72
  24. 2015Seeing through the Human Reporting Bias: Visual Classifiers from Noisy Human-Centric Labelscited by 64
  25. 2021Understanding and Mitigating Annotation Bias in Facial Expression Recognitioncited by 50
  26. 2021Consistent Instance False Positive Improves Fairness in Face Recognitioncited by 40
  27. 2021Learning Fair Classifiers with Partially Annotated Group Labelscited by 40
  28. 2020Gender Slopes: Counterfactual Fairness for Computer Vision Models by Attribute Manipulationcited by 37
  29. 2019Transfer of Machine Learning Fairness across Domainscited by 36
  30. 2022Measuring Representational Harms in Image Captioningcited by 36
  31. 2020Face Quality Estimation and Its Correlation to Demographic and Non-Demographic Bias in Face Recognitioncited by 31
  32. 2018Coreset-Based Neural Network Compressioncited by 27
  33. 2020Understanding Fairness of Gender Classification Algorithms Across Gender-Race Groupscited by 24
  34. 2021Rethinking Common Assumptions to Mitigate Racial Bias in Face Recognition Datasetscited by 22
  35. 2020Investigating Bias in Deep Face Analysis: The KANFace Dataset and Empirical Studycited by 18
  36. 2021Simon Says: Evaluating and Mitigating Bias in Pruned Neural Networks with Knowledge Distillationcited by 15
  37. 2019COP: Customized Deep Model Compression via Regularized Correlation-Based Filter-Level Pruningcited by 14
  38. 2022The Effect of Model Compression on Fairness in Facial Expression Recognitioncited by 13

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 4; 2023: 8; 2024: 11; 2025: 6; 2026: 1.

30 papers.

Sort:

By area:

  1. 2023Structured Pruning for Deep Convolutional Neural Networks: A surveycited by 122
  2. 2022Pruning's Effect on Generalization Through the Lens of Training and Regularizationcited by 31
  3. 2022Rethinking Bias Mitigation: Fairer Architectures Make for Fairer Face Recognitioncited by 26
  4. 2024BiasPruner: Debiased Continual Learning for Medical Image Classificationcited by 12
  5. 2023Bias in Pruned Vision Models: In-Depth Analysis and Countermeasurescited by 11
  6. 2024Achieve Fairness without Demographics for Dermatological Disease Diagnosiscited by 10
  7. 2022Causality-Inspired Taxonomy for Explainable Artificial Intelligencecited by 9
  8. 2023Learning Informative Representation for Fairness-aware Multivariate Time-series Forecasting: A Group-based Perspectivecited by 8
  9. 2023Balancing Act: Constraining Disparate Impact in Sparse Modelscited by 7
  10. 2024LayerMerge: Neural Network Depth Compression through Layer Pruning and Mergingcited by 7
  11. 2025Review of Demographic Fairness in Face Recognitioncited by 7
  12. 2023Debiased Distillation by Transplanting the Last Layercited by 6
18 more
  1. 2024A Large-Scale Empirical Study on Improving the Fairness of Image Classification Modelscited by 6
  2. 2024Model Compression Techniques in Biometrics Applications: A Surveycited by 5
  3. 2023The Casual Conversations v2 Datasetcited by 4
  4. 2022COLT: Cyclic Overlapping Lottery Tickets for Faster Pruning of Convolutional Neural Networkscited by 3
  5. 2024FineFACE: Fair Facial Attribute Classification Leveraging Fine-grained Featurescited by 3
  6. 2025Neuroplasticity in Artificial Intelligence -- An Overview and Inspirations on Drop In & Out Learningcited by 3
  7. 2024A Self-Supervised Learning Pipeline for Demographically Fair Facial Attribute Classificationcited by 2
  8. 2024You Never Know: Quantization Induces Inconsistent Biases in Vision-Language Foundation Modelscited by 2
  9. 2025Enhancing Fairness in Skin Lesion Classification for Medical Diagnosis Using Prune Learningcited by 2
  10. 2023Integrating Fairness and Model Pruning Through Bi-level Optimizationcited by 1
  11. 2024Will the Inclusion of Generated Data Amplify Bias Across Generations in Future Image Classification Models?cited by 1
  12. 2024Improving Bias in Facial Attribute Classification: A Combined Impact of KL Divergence induced Loss Function and Dual Attentioncited by 1
  13. 2025Evaluating Fairness and Mitigating Bias in Machine Learning: A Novel Technique using Tensor Data and Bayesian Regressioncited by 1
  14. 2023Beta-Rank: A Robust Convolutional Filter Pruning Method For Imbalanced Medical Image Analysiscited by 0
  15. 2024Accelerating Federated Learning by Selecting Beneficial Herd of Local Gradientscited by 0
  16. 2025A Feature-level Bias Evaluation Framework for Facial Expression Recognition Modelscited by 0
  17. 2025Leveraging Text Guidance for Enhancing Demographic Fairness in Gender Classificationcited by 0
  18. 2026FairQuant: Fairness-Aware Mixed-Precision Quantization for Medical Image Classificationcited by 0