mlsanityData to 14 Oct 2026

CILIATE: Towards Fairer Class-based Incremental Learning by Dataset and Training Refinement

arXiv 2304.04222 ↗First posted 9 Apr 2023cs.LG cs.AI cs.CYcited by 1

Not on the map. Why?

Abstract (arXiv)

Due to the model aging problem, Deep Neural Networks (DNNs) need updates to adjust them to new data distributions. The common practice leverages incremental learning (IL), e.g., Class-based Incremental Learning (CIL) that updates output labels, to update the model with new data and a limited number of old data. This avoids heavyweight training (from scratch) using conventional methods and saves storage space by reducing the number of old data to store. But it also leads to poor performance in fairness. In this paper, we show that CIL suffers both dataset and algorithm bias problems, and existing solutions can only partially solve the problem. We propose a novel framework, CILIATE, that fixes both dataset and algorithm bias in CIL. It features a novel differential analysis guided dataset and training refinement process that identifies unique and important samples overlooked by existing CIL and enforces the model to learn from them. Through this process, CILIATE improves the fairness of CIL by 17.03%, 22.46%, and 31.79% compared to state-of-the-art methods, iCaRL, BiC, and WA, respectively, based on our evaluation on three popular datasets and widely used ResNet models.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 48 of its 98 references that are in the map. First posted on arXiv 9 Apr 2023.

Builds on

48 of 98 references.

References · 48

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  3. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  4. 2016Learning without Forgettingcited by 2,496
  5. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,333
  6. 2016Equality of Opportunity in Supervised Learningcited by 2,007
  7. 2019Energy and Policy Considerations for Deep Learning in NLPcited by 1,254
  8. 2017Memory Aware Synapses: Learning what (not) to forgetcited by 1,105
  9. 2016End to End Learning for Self-Driving Carscited by 1,009
  10. 2018Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigencecited by 742
  11. 2019Large Scale Incremental Learningcited by 732
  12. 2014Certifying and removing disparate impactcited by 715
36 more
  1. 2018Mitigating Unwanted Biases with Adversarial Learningcited by 663
  2. 2018End-to-End Incremental Learningcited by 597
  3. 2021Just Train Twice: Improving Group Robustness without Training Group Informationcited by 523
  4. 2017A systematic study of the class imbalance problem in convolutional neural networkscited by 513
  5. 2017On Fairness and Calibrationcited by 406
  6. 2016Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatmentcited by 369
  7. 2021DER: Dynamically Expandable Representation for Class Incremental Learningcited by 355
  8. 2018Not All Samples Are Created Equal: Deep Learning with Importance Samplingcited by 328
  9. 2017Fairness in Criminal Justice Risk Assessments: The State of the Artcited by 315
  10. 2017DeepXplore: Automated Whitebox Testing of Deep Learning Systemscited by 311
  11. 2019Maintaining Discrimination and Fairness in Class Incremental Learningcited by 283
  12. 2017Overcoming Catastrophic Forgetting by Incremental Moment Matchingcited by 243
  13. 2020Semantic Drift Compensation for Class-Incremental Learningcited by 241
  14. 2018Re-evaluating Continual Learning Scenarios: A Categorization and Case for Strong Baselinescited by 228
  15. 2020Measuring and Reducing Gendered Correlations in Pre-trained Modelscited by 224
  16. 2019Compacting, Picking and Growing for Unforgetting Continual Learningcited by 207
  17. 2019Learning to Remember: A Synaptic Plasticity Driven Framework for Continual Learningcited by 182
  18. 2019Mitigating Bias in Algorithmic Hiring: Evaluating Claims and Practicescited by 174
  19. 2017Data Decisions and Theoretical Implications when Adversarially Learning Fair Representationscited by 165
  20. 2018FairGAN: Fairness-aware Generative Adversarial Networkscited by 164
  21. 2014A Convolutional Neural Network for Modelling Sentencescited by 163
  22. 2017Fairness Testing: Testing Software for Discriminationcited by 126
  23. 2020The Cost of Training NLP Models: A Concise Overviewcited by 98
  24. 2020Estimating Example Difficulty Using Variance of Gradientscited by 97
  25. 2019Continual Learning for Robotics: Definition, Framework, Learning Strategies, Opportunities and Challengescited by 93
  26. 2015Convolutional Neural Network Architectures for Matching Natural Language Sentencescited by 82
  27. 2018Automated Directed Fairness Testingcited by 78
  28. 2016A Confidence-Based Approach for Balancing Fairness and Accuracycited by 73
  29. 2021NeuronFair: Interpretable White-Box Fairness Testing through Biased Neuron Identificationcited by 42
  30. 2021Analysis and Applications of Class-wise Robustness in Adversarial Trainingcited by 33
  31. 2016Achieving non-discrimination in data releasecited by 23
  32. 2018A 64mW DNN-based Visual Navigation Engine for Autonomous Nano-Dronescited by 23
  33. 2018Automated Test Generation to Detect Individual Discrimination in AI Modelscited by 21
  34. 2022FairNeuron: Improving Deep Neural Network Fairness with Adversary Games on Selective Neuronscited by 21
  35. 2021FairMask: Better Fairness via Model-based Rebalancing of Protected Attributescited by 19
  36. 2018Distributed Weight Consolidation: A Brain Segmentation Case Studycited by 9

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024Efficient DNN-Powered Software with Fair Sparse Modelscited by 0