Fairness Improves Learning from Noisily Labeled Long-Tailed Data

• URL: http://arxiv.org/abs/2303.12291v1
• Date: Wed, 22 Mar 2023 03:46:51 GMT
• Title: Fairness Improves Learning from Noisily Labeled Long-Tailed Data
• Authors: Jiaheng Wei, Zhaowei Zhu, Gang Niu, Tongliang Liu, Sijia Liu, Masashi Sugiyama, and Yang Liu
• Abstract summary: Long-tailed and noisily labeled data frequently appear in real-world applications and impose significant challenges for learning. We introduce the Fairness Regularizer (FR), inspired by regularizing the performance gap between any two sub-populations. We show that the introduced fairness regularizer improves the performances of sub-populations on the tail and the overall learning performance.
• Score: 119.0612617460727
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Both long-tailed and noisily labeled data frequently appear in real-world applications and impose significant challenges for learning. Most prior works treat either problem in an isolated way and do not explicitly consider the coupling effects of the two. Our empirical observation reveals that such solutions fail to consistently improve the learning when the dataset is long-tailed with label noise. Moreover, with the presence of label noise, existing methods do not observe universal improvements across different sub-populations; in other words, some sub-populations enjoyed the benefits of improved accuracy at the cost of hurting others. Based on these observations, we introduce the Fairness Regularizer (FR), inspired by regularizing the performance gap between any two sub-populations. We show that the introduced fairness regularizer improves the performances of sub-populations on the tail and the overall learning performance. Extensive experiments demonstrate the effectiveness of the proposed solution when complemented with certain existing popular robust or class-balanced methods.

Related papers

• Gradient Reweighting: Towards Imbalanced Class-Incremental Learning [8.438092346233054]
  Class-Incremental Learning (CIL) trains a model to continually recognize new classes from non-stationary data. A major challenge of CIL arises when applying to real-world data characterized by non-uniform distribution. We show that this dual imbalance issue causes skewed gradient updates with biased weights in FC layers, thus inducing over/under-fitting and catastrophic forgetting in CIL.
  arXiv  Detail & Related papers  (2024-02-28T18:08:03Z)
• Adaptive End-to-End Metric Learning for Zero-Shot Cross-Domain Slot Filling [2.6056468338837457]
  Slot filling poses a critical challenge to handle a novel domain whose samples are never seen during training. Most prior works deal with this problem in a two-pass pipeline manner based on metric learning. We propose a new adaptive end-to-end metric learning scheme for the challenging zero-shot slot filling.
  arXiv  Detail & Related papers  (2023-10-23T19:01:16Z)
• Beyond Myopia: Learning from Positive and Unlabeled Data through Holistic Predictive Trends [26.79150786180822]
  We unveil an intriguing yet long-overlooked observation in PUL. Predictive trends for positive and negative classes display distinctly different patterns. We propose a novel TPP-inspired measure for trend detection and prove its unbiasedness in predicting changes.
  arXiv  Detail & Related papers  (2023-10-06T08:06:15Z)
• Late Stopping: Avoiding Confidently Learning from Mislabeled Examples [61.00103151680946]
  We propose a new framework, Late Stopping, which leverages the intrinsic robust learning ability of DNNs through a prolonged training process. We empirically observe that mislabeled and clean examples exhibit differences in the number of epochs required for them to be consistently and correctly classified. Experimental results on benchmark-simulated and real-world noisy datasets demonstrate that the proposed method outperforms state-of-the-art counterparts.
  arXiv  Detail & Related papers  (2023-08-26T12:43:25Z)
• Co-Learning Meets Stitch-Up for Noisy Multi-label Visual Recognition [70.00984078351927]
  This paper focuses on reducing noise based on some inherent properties of multi-label classification and long-tailed learning under noisy cases. We propose a Stitch-Up augmentation to synthesize a cleaner sample, which directly reduces multi-label noise. A Heterogeneous Co-Learning framework is further designed to leverage the inconsistency between long-tailed and balanced distributions.
  arXiv  Detail & Related papers  (2023-07-03T09:20:28Z)
• Scaling Up Semi-supervised Learning with Unconstrained Unlabelled Data [27.75143621836449]
  We propose UnMixMatch, a semi-supervised learning framework which can learn effective representations from unconstrained data. We perform extensive experiments on 4 commonly used datasets and demonstrate superior performance over existing semi-supervised methods with a performance boost of 4.79%.
  arXiv  Detail & Related papers  (2023-06-02T01:07:14Z)
• On Modality Bias Recognition and Reduction [70.69194431713825]
  We study the modality bias problem in the context of multi-modal classification. We propose a plug-and-play loss function method, whereby the feature space for each label is adaptively learned. Our method yields remarkable performance improvements compared with the baselines.
  arXiv  Detail & Related papers  (2022-02-25T13:47:09Z)
• Semi-supervised Long-tailed Recognition using Alternate Sampling [95.93760490301395]
  Main challenges in long-tailed recognition come from the imbalanced data distribution and sample scarcity in its tail classes. We propose a new recognition setting, namely semi-supervised long-tailed recognition. We demonstrate significant accuracy improvements over other competitive methods on two datasets.
  arXiv  Detail & Related papers  (2021-05-01T00:43:38Z)
• 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)

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.