BatMan-CLR: Making Few-shots Meta-Learners Resilient Against Label Noise

• URL: http://arxiv.org/abs/2309.06046v1
• Date: Tue, 12 Sep 2023 08:30:35 GMT
• Title: BatMan-CLR: Making Few-shots Meta-Learners Resilient Against Label Noise
• Authors: Jeroen M. Galjaard, Robert Birke, Juan Perez, Lydia Y. Chen
• Abstract summary: We present the first analysis of the impact of varying levels of label noise on the performance of state-of-the-art meta-learners. We show that the accuracy of Reptile, iMAML, and foMAML drops by up to 42% on the Omniglot and CifarFS datasets when meta-training is affected by label noise. We propose two sampling techniques, namely manifold (Man) and batch manifold (BatMan), which transform the noisy supervised learners into semi-supervised ones.
• Score: 5.67944073225624
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The negative impact of label noise is well studied in classical supervised learning yet remains an open research question in meta-learning. Meta-learners aim to adapt to unseen learning tasks by learning a good initial model in meta-training and consecutively fine-tuning it according to new tasks during meta-testing. In this paper, we present the first extensive analysis of the impact of varying levels of label noise on the performance of state-of-the-art meta-learners, specifically gradient-based $N$-way $K$-shot learners. We show that the accuracy of Reptile, iMAML, and foMAML drops by up to 42% on the Omniglot and CifarFS datasets when meta-training is affected by label noise. To strengthen the resilience against label noise, we propose two sampling techniques, namely manifold (Man) and batch manifold (BatMan), which transform the noisy supervised learners into semi-supervised ones to increase the utility of noisy labels. We first construct manifold samples of $N$-way $2$-contrastive-shot tasks through augmentation, learning the embedding via a contrastive loss in meta-training, and then perform classification through zeroing on the embedding in meta-testing. We show that our approach can effectively mitigate the impact of meta-training label noise. Even with 60% wrong labels \batman and \man can limit the meta-testing accuracy drop to ${2.5}$, ${9.4}$, ${1.1}$ percent points, respectively, with existing meta-learners across the Omniglot, CifarFS, and MiniImagenet datasets.

Related papers

• Enhanced Meta Label Correction for Coping with Label Corruption [3.6804038214708577]
  We propose an Enhanced Meta Label Correction approach abbreviated asC for the learning with noisy labels problem. TraditionalC outperforms prior approaches and achieves state-of-the-art results in all standard benchmarks.
  arXiv  Detail & Related papers  (2023-05-22T12:11:07Z)
• Pseudo-Labeling Based Practical Semi-Supervised Meta-Training for Few-Shot Learning [93.63638405586354]
  We propose a simple and effective meta-training framework, called pseudo-labeling based meta-learning (PLML) Firstly, we train a classifier via common semi-supervised learning (SSL) and use it to obtain the pseudo-labels of unlabeled data. We build few-shot tasks from labeled and pseudo-labeled data and design a novel finetuning method with feature smoothing and noise suppression.
  arXiv  Detail & Related papers  (2022-07-14T10:53:53Z)
• Robust Meta-learning with Sampling Noise and Label Noise via Eigen-Reptile [78.1212767880785]
  meta-learner is prone to overfitting since there are only a few available samples. When handling the data with noisy labels, the meta-learner could be extremely sensitive to label noise. We present Eigen-Reptile (ER) that updates the meta- parameters with the main direction of historical task-specific parameters.
  arXiv  Detail & Related papers  (2022-06-04T08:48:02Z)
• Negative Inner-Loop Learning Rates Learn Universal Features [0.0]
  We study the effect that a learned learning-rate has on the per-task feature representations in Meta-SGD. Negative learning rates push features away from task-specific features and towards task-agnostic features. This confirms the hypothesis that Meta-SGD's negative learning rates cause the model to learn task-agnostic features rather than simply adapt to task specific features.
  arXiv  Detail & Related papers  (2022-03-18T22:43:16Z)
• Training Classifiers that are Universally Robust to All Label Noise Levels [91.13870793906968]
  Deep neural networks are prone to overfitting in the presence of label noise. We propose a distillation-based framework that incorporates a new subcategory of Positive-Unlabeled learning. Our framework generally outperforms at medium to high noise levels.
  arXiv  Detail & Related papers  (2021-05-27T13:49:31Z)
• Multi-Objective Interpolation Training for Robustness to Label Noise [17.264550056296915]
  We show that standard supervised contrastive learning degrades in the presence of label noise. We propose a novel label noise detection method that exploits the robust feature representations learned via contrastive learning. Experiments on synthetic and real-world noise benchmarks demonstrate that MOIT/MOIT+ achieves state-of-the-art results.
  arXiv  Detail & Related papers  (2020-12-08T15:01:54Z)
• Meta Soft Label Generation for Noisy Labels [0.0]
  We propose a Meta Soft Label Generation algorithm called MSLG. MSLG can jointly generate soft labels using meta-learning techniques. Our approach outperforms other state-of-the-art methods by a large margin.
  arXiv  Detail & Related papers  (2020-07-11T19:37:44Z)
• Meta Transition Adaptation for Robust Deep Learning with Noisy Labels [61.8970957519509]
  This study proposes a new meta-transition-learning strategy for the task. Specifically, through the sound guidance of a small set of meta data with clean labels, the noise transition matrix and the classifier parameters can be mutually ameliorated. Our method can more accurately extract the transition matrix, naturally following its more robust performance than prior arts.
  arXiv  Detail & Related papers  (2020-06-10T07:27:25Z)
• Learning Not to Learn in the Presence of Noisy Labels [104.7655376309784]
  We show that a new class of loss functions called the gambler's loss provides strong robustness to label noise across various levels of corruption. We show that training with this loss function encourages the model to "abstain" from learning on the data points with noisy labels.
  arXiv  Detail & Related papers  (2020-02-16T09:12:27Z)
• Incremental Meta-Learning via Indirect Discriminant Alignment [118.61152684795178]
  We develop a notion of incremental learning during the meta-training phase of meta-learning. Our approach performs favorably at test time as compared to training a model with the full meta-training set.
  arXiv  Detail & Related papers  (2020-02-11T01:39:12Z)

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.