Fair Class-Incremental Learning using Sample Weighting

• URL: http://arxiv.org/abs/2410.01324v1
• Date: Wed, 2 Oct 2024 08:32:21 GMT
• Title: Fair Class-Incremental Learning using Sample Weighting
• Authors: Jaeyoung Park, Minsu Kim, Steven Euijong Whang,
• Abstract summary: We show that naively using all the samples of the current task for training results in unfair catastrophic forgetting for certain sensitive groups including classes. We propose a fair class-incremental learning framework that adjusts the training weights of current task samples to change the direction of the average gradient vector. Experiments show that FSW achieves better accuracy-fairness tradeoff results than state-of-the-art approaches on real datasets.
• Score: 27.82760149957115
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Model fairness is becoming important in class-incremental learning for Trustworthy AI. While accuracy has been a central focus in class-incremental learning, fairness has been relatively understudied. However, naively using all the samples of the current task for training results in unfair catastrophic forgetting for certain sensitive groups including classes. We theoretically analyze that forgetting occurs if the average gradient vector of the current task data is in an "opposite direction" compared to the average gradient vector of a sensitive group, which means their inner products are negative. We then propose a fair class-incremental learning framework that adjusts the training weights of current task samples to change the direction of the average gradient vector and thus reduce the forgetting of underperforming groups and achieve fairness. For various group fairness measures, we formulate optimization problems to minimize the overall losses of sensitive groups while minimizing the disparities among them. We also show the problems can be solved with linear programming and propose an efficient Fairness-aware Sample Weighting (FSW) algorithm. Experiments show that FSW achieves better accuracy-fairness tradeoff results than state-of-the-art approaches on real datasets.

Related papers

• Boosting Fair Classifier Generalization through Adaptive Priority Reweighing [59.801444556074394]
  A performance-promising fair algorithm with better generalizability is needed. This paper proposes a novel adaptive reweighing method to eliminate the impact of the distribution shifts between training and test data on model generalizability.
  arXiv  Detail & Related papers  (2023-09-15T13:04:55Z)
• Bias Amplification Enhances Minority Group Performance [10.380812738348899]
  We propose BAM, a novel two-stage training algorithm. In the first stage, the model is trained using a bias amplification scheme via introducing a learnable auxiliary variable for each training sample. In the second stage, we upweight the samples that the bias-amplified model misclassifies, and then continue training the same model on the reweighted dataset.
  arXiv  Detail & Related papers  (2023-09-13T04:40:08Z)
• Fair Few-shot Learning with Auxiliary Sets [53.30014767684218]
  In many machine learning (ML) tasks, only very few labeled data samples can be collected, which can lead to inferior fairness performance. In this paper, we define the fairness-aware learning task with limited training samples as the emphfair few-shot learning problem. We devise a novel framework that accumulates fairness-aware knowledge across different meta-training tasks and then generalizes the learned knowledge to meta-test tasks.
  arXiv  Detail & Related papers  (2023-08-28T06:31:37Z)
• FairAdaBN: Mitigating unfairness with adaptive batch normalization and its application to dermatological disease classification [14.589159162086926]
  We propose FairAdaBN, which makes batch normalization adaptive to sensitive attribute. We propose a new metric, named Fairness-Accuracy Trade-off Efficiency (FATE), to compute normalized fairness improvement over accuracy drop. Experiments on two dermatological datasets show that our proposed method outperforms other methods on fairness criteria and FATE.
  arXiv  Detail & Related papers  (2023-03-15T02:22:07Z)
• Chasing Fairness Under Distribution Shift: A Model Weight Perturbation Approach [72.19525160912943]
  We first theoretically demonstrate the inherent connection between distribution shift, data perturbation, and model weight perturbation. We then analyze the sufficient conditions to guarantee fairness for the target dataset. Motivated by these sufficient conditions, we propose robust fairness regularization (RFR)
  arXiv  Detail & Related papers  (2023-03-06T17:19:23Z)
• Fair and Optimal Classification via Post-Processing [10.163721748735801]
  This paper provides a complete characterization of the inherent tradeoff of demographic parity on classification problems. We show that the minimum error rate achievable by randomized and attribute-aware fair classifiers is given by the optimal value of a Wasserstein-barycenter problem.
  arXiv  Detail & Related papers  (2022-11-03T00:04:04Z)
• FairIF: Boosting Fairness in Deep Learning via Influence Functions with Validation Set Sensitive Attributes [51.02407217197623]
  We propose a two-stage training algorithm named FAIRIF. It minimizes the loss over the reweighted data set where the sample weights are computed. We show that FAIRIF yields models with better fairness-utility trade-offs against various types of bias.
  arXiv  Detail & Related papers  (2022-01-15T05:14:48Z)
• Can Active Learning Preemptively Mitigate Fairness Issues? [66.84854430781097]
  dataset bias is one of the prevailing causes of unfairness in machine learning. We study whether models trained with uncertainty-based ALs are fairer in their decisions with respect to a protected class. We also explore the interaction of algorithmic fairness methods such as gradient reversal (GRAD) and BALD.
  arXiv  Detail & Related papers  (2021-04-14T14:20:22Z)
• Fairness Constraints in Semi-supervised Learning [56.48626493765908]
  We develop a framework for fair semi-supervised learning, which is formulated as an optimization problem. We theoretically analyze the source of discrimination in semi-supervised learning via bias, variance and noise decomposition. Our method is able to achieve fair semi-supervised learning, and reach a better trade-off between accuracy and fairness than fair supervised learning.
  arXiv  Detail & Related papers  (2020-09-14T04:25:59Z)
• Ensuring Fairness Beyond the Training Data [22.284777913437182]
  We develop classifiers that are fair with respect to the training distribution and for a class of perturbations. Based on online learning algorithm, we develop an iterative algorithm that converges to a fair and robust solution. Our experiments show that there is an inherent trade-off between fairness and accuracy of such classifiers.
  arXiv  Detail & Related papers  (2020-07-12T16:20:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.