mlsanityData to 7 Oct 2026

A Fair Loss Function for Network Pruning

arXiv 2211.10285 ↗First posted 18 Nov 2022cs.LG cs.CYcited by 4

Not on the map. Why?

Abstract (arXiv)

Model pruning can enable the deployment of neural networks in environments with resource constraints. While pruning may have a small effect on the overall performance of the model, it can exacerbate existing biases into the model such that subsets of samples see significantly degraded performance. In this paper, we introduce the performance weighted loss function, a simple modified cross-entropy loss function that can be used to limit the introduction of biases during pruning. Experiments using the CelebA, Fitzpatrick17k and CIFAR-10 datasets demonstrate that the proposed method is a simple and effective tool that can enable existing pruning methods to be used in fairness sensitive contexts. Code used to produce all experiments contained in this paper can be found at https://github.com/robbiemeyer/pw_loss_pruning.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 24 of its 40 references that are in the map. First posted on arXiv 18 Nov 2022.

Builds on

24 of 40 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  5. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  6. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  7. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 1,998
  8. 2016Pruning Filters for Efficient ConvNetscited by 1,129
  9. 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,127
  10. 2020What is the State of Neural Network Pruning?cited by 578
  11. 2019Importance Estimation for Neural Network Pruningcited by 531
  12. 2017ThiNet: A Filter Level Pruning Method for Deep Neural Network Compressioncited by 438
12 more
  1. 2019Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classificationcited by 396
  2. 2021Evaluating Deep Neural Networks Trained on Clinical Images in Dermatology with the Fitzpatrick 17k Datasetcited by 184
  3. 2020Characterising Bias in Compressed Modelscited by 162
  4. 2020CheXclusion: Fairness gaps in deep chest X-ray classifierscited by 153
  5. 2019Gate Decorator: Global Filter Pruning Method for Accelerating Deep Convolutional Neural Networkscited by 118
  6. 2016An Analysis of Deep Neural Network Models for Practical Applicationscited by 114
  7. 2022FairPrune: Achieving Fairness Through Pruning for Dermatological Disease Diagnosiscited by 59
  8. 2020Prune Responsiblycited by 20
  9. 2022Can Model Compression Improve NLP Fairnesscited by 18
  10. 2020Going Beyond Classification Accuracy Metrics in Model Compressioncited by 15
  11. 2022Debiasing Deep Chest X-Ray Classifiers using Intra- and Post-processing Methodscited by 15
  12. 2021Automatic Neural Network Pruning that Efficiently Preserves the Model Accuracycited by 4

Built on by

Cited by year (2026 to 7 Oct)

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

4 papers.

  1. 2025Enhancing Fairness in Skin Lesion Classification for Medical Diagnosis Using Prune Learningcited by 2
  2. 2024Understanding and Reducing the Class-Dependent Effects of Data Augmentation with A Two-Player Game Approachcited by 0
  3. 2025Mitigating Individual Skin Tone Bias in Skin Lesion Classification through Distribution-Aware Reweightingcited by 0
  4. 2026Bias In, Bias Out? Finding Unbiased Subnetworks in Vanilla Modelscited by 0