mlsanityData to 14 Oct 2026

Efficient DNN-Powered Software with Fair Sparse Models

arXiv 2407.02805 ↗First posted 3 Jul 2024cs.SE cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

With the emergence of the Software 3.0 era, there is a growing trend of compressing and integrating large models into software systems, with significant societal implications. Regrettably, in numerous instances, model compression techniques impact the fairness performance of these models and thus the ethical behavior of DNN-powered software. One of the most notable example is the Lottery Ticket Hypothesis (LTH), a prevailing model pruning approach. This paper demonstrates that fairness issue of LTHbased pruning arises from both its subnetwork selection and training procedures, highlighting the inadequacy of existing remedies. To address this, we propose a novel pruning framework, Ballot, which employs a novel conflict-detection-based subnetwork selection to find accurate and fair subnetworks, coupled with a refined training process to attain a high-performance model, thereby improving the fairness of DNN-powered software. By means of this procedure, Ballot improves the fairness of pruning by 38.00%, 33.91%, 17.96%, and 35.82% compared to state-of-the-art baselines, namely Magnitude Pruning, Standard LTH, SafeCompress, and FairScratch respectively, based on our evaluation of five popular datasets and three widely used models. Our code is available at https://anonymous.4open.science/r/Ballot-506E.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 48 of its 94 references that are in the map. First posted on arXiv 3 Jul 2024.

Builds on

48 of 94 references.

References · 48

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  5. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  6. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  7. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
  8. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,262
  9. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 2,031
  10. 2016Equality of Opportunity in Supervised Learningcited by 2,007
  11. 2020Shortcut Learning in Deep Neural Networkscited by 1,969
  12. 2016Pruning Filters for Efficient ConvNetscited by 1,143
36 more
  1. 2014Certifying and removing disparate impactcited by 715
  2. 2018Mitigating Unwanted Biases with Adversarial Learningcited by 663
  3. 2019Linear Mode Connectivity and the Lottery Ticket Hypothesiscited by 637
  4. 2019Green AIcited by 627
  5. 2019Importance Estimation for Neural Network Pruningcited by 541
  6. 2013Do Deep Nets Really Need to be Deep?cited by 474
  7. 2018Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Accelerationcited by 367
  8. 2022Estimating the Carbon Footprint of BLOOM, a 176B Parameter Language Modelcited by 265
  9. 2021Pruning and Quantization for Deep Neural Network Acceleration: A Surveycited by 263
  10. 2016Demographic Dialectal Variation in Social Media: A Case Study of African-American Englishcited by 196
  11. 2019Mitigating Bias in Algorithmic Hiring: Evaluating Claims and Practicescited by 174
  12. 2017Data Decisions and Theoretical Implications when Adversarially Learning Fair Representationscited by 165
  13. 2018FairGAN: Fairness-aware Generative Adversarial Networkscited by 164
  14. 2017Fairness Testing: Testing Software for Discriminationcited by 126
  15. 2020Degree-Quant: Quantization-Aware Training for Graph Neural Networkscited by 96
  16. 2018Automated Directed Fairness Testingcited by 78
  17. 2021Software Engineering for AI-Based Systems: A Surveycited by 69
  18. 2022FairPrune: Achieving Fairness Through Pruning for Dermatological Disease Diagnosiscited by 59
  19. 2021Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot?cited by 52
  20. 2020Robustness May Be at Odds with Fairness: An Empirical Study on Class-wise Accuracycited by 45
  21. 2017An Entropy-based Pruning Method for CNN Compressioncited by 37
  22. 2021Analysis and Applications of Class-wise Robustness in Adversarial Trainingcited by 33
  23. 2020A Survey on Deep Neural Network Compression: Challenges, Overview, and Solutionscited by 32
  24. 2021BiasFinder: Metamorphic Test Generation to Uncover Bias for Sentiment Analysis Systemscited by 24
  25. 2016Achieving non-discrimination in data releasecited by 23
  26. 2018Automated Test Generation to Detect Individual Discrimination in AI Modelscited by 21
  27. 2022FairNeuron: Improving Deep Neural Network Fairness with Adversary Games on Selective Neuronscited by 21
  28. 2022Compressing Pre-trained Models of Code into 3 MBcited by 21
  29. 2020Prune Responsiblycited by 20
  30. 2021Simon Says: Evaluating and Mitigating Bias in Pruned Neural Networks with Knowledge Distillationcited by 15
  31. 2022Can pruning improve certified robustness of neural networks?cited by 14
  32. 2020WrapNet: Neural Net Inference with Ultra-Low-Resolution Arithmeticcited by 12
  33. 2021BiasRV: Uncovering Biased Sentiment Predictions at Runtimecited by 12
  34. 2022QVIP: An ILP-based Formal Verification Approach for Quantized Neural Networkscited by 12
  35. 2022Safety and Performance, Why not Both? Bi-Objective Optimized Model Compression toward AI Software Deploymentcited by 8
  36. 2023CILIATE: Towards Fairer Class-based Incremental Learning by Dataset and Training Refinementcited by 1

Built on by

Not cited yet.