Learning with Confidence: Training Better Classifiers from Soft Labels
- URL: http://arxiv.org/abs/2409.16071v1
- Date: Tue, 24 Sep 2024 13:12:29 GMT
- Title: Learning with Confidence: Training Better Classifiers from Soft Labels
- Authors: Sjoerd de Vries, Dirk Thierens,
- Abstract summary: In supervised machine learning, models are typically trained using data with hard labels, i.e., definite assignments of class membership.
We investigate whether incorporating label uncertainty, represented as discrete probability distributions over the class labels, improves the predictive performance of classification models.
- Score: 0.0
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: In supervised machine learning, models are typically trained using data with hard labels, i.e., definite assignments of class membership. This traditional approach, however, does not take the inherent uncertainty in these labels into account. We investigate whether incorporating label uncertainty, represented as discrete probability distributions over the class labels -- known as soft labels -- improves the predictive performance of classification models. We first demonstrate the potential value of soft label learning (SLL) for estimating model parameters in a simulation experiment, particularly for limited sample sizes and imbalanced data. Subsequently, we compare the performance of various wrapper methods for learning from both hard and soft labels using identical base classifiers. On real-world-inspired synthetic data with clean labels, the SLL methods consistently outperform hard label methods. Since real-world data is often noisy and precise soft labels are challenging to obtain, we study the effect that noisy probability estimates have on model performance. Alongside conventional noise models, our study examines four types of miscalibration that are known to affect human annotators. The results show that SLL methods outperform the hard label methods in the majority of settings. Finally, we evaluate the methods on a real-world dataset with confidence scores, where the SLL methods are shown to match the traditional methods for predicting the (noisy) hard labels while providing more accurate confidence estimates.
Related papers
- Robust Partial-Label Learning by Leveraging Class Activation Values [0.0]
Real-world training data is often noisy; for example, human annotators assign conflicting class labels to the same instances.
We propose a novel method based on subjective logic, which explicitly represents uncertainty by leveraging the magnitudes of the underlying neural network's class activation values.
We empirically show that our method yields more robust predictions in terms of predictive performance under high noise levels.
arXiv Detail & Related papers (2025-02-17T12:30:05Z) - Efficient Adaptive Label Refinement for Label Noise Learning [14.617885790129336]
We propose Adaptive Label Refinement (ALR) to avoid incorrect labels and thoroughly learning clean samples.
ALR is simple and efficient, requiring no prior knowledge of noise or auxiliary datasets.
We validate ALR's effectiveness through experiments on benchmark datasets with artificial label noise (CIFAR-10/100) and real-world datasets with inherent noise (ANIMAL-10N, Clothing1M, WebVision)
arXiv Detail & Related papers (2025-02-01T09:58:08Z) - Learning from Ambiguous Data with Hard Labels [34.06499138206804]
Real-world data often contains intrinsic ambiguity that the common single-hard-label annotation paradigm ignores.
Standard training using ambiguous data with hard labels may produce overly confident models and thus leading to poor generalization.
We propose a novel framework called Quantized Label Learning (QLL) to alleviate this issue.
arXiv Detail & Related papers (2025-01-03T14:54:49Z) - Boosting Semi-Supervised Learning by bridging high and low-confidence
predictions [4.18804572788063]
Pseudo-labeling is a crucial technique in semi-supervised learning (SSL)
We propose a new method called ReFixMatch, which aims to utilize all of the unlabeled data during training.
arXiv Detail & Related papers (2023-08-15T00:27:18Z) - Channel-Wise Contrastive Learning for Learning with Noisy Labels [60.46434734808148]
We introduce channel-wise contrastive learning (CWCL) to distinguish authentic label information from noise.
Unlike conventional instance-wise contrastive learning (IWCL), CWCL tends to yield more nuanced and resilient features aligned with the authentic labels.
Our strategy is twofold: firstly, using CWCL to extract pertinent features to identify cleanly labeled samples, and secondly, progressively fine-tuning using these samples.
arXiv Detail & Related papers (2023-08-14T06:04:50Z) - Label-Retrieval-Augmented Diffusion Models for Learning from Noisy
Labels [61.97359362447732]
Learning from noisy labels is an important and long-standing problem in machine learning for real applications.
In this paper, we reformulate the label-noise problem from a generative-model perspective.
Our model achieves new state-of-the-art (SOTA) results on all the standard real-world benchmark datasets.
arXiv Detail & Related papers (2023-05-31T03:01:36Z) - SoftMatch: Addressing the Quantity-Quality Trade-off in Semi-supervised
Learning [101.86916775218403]
This paper revisits the popular pseudo-labeling methods via a unified sample weighting formulation.
We propose SoftMatch to overcome the trade-off by maintaining both high quantity and high quality of pseudo-labels during training.
In experiments, SoftMatch shows substantial improvements across a wide variety of benchmarks, including image, text, and imbalanced classification.
arXiv Detail & Related papers (2023-01-26T03:53:25Z) - Debiased Pseudo Labeling in Self-Training [77.83549261035277]
Deep neural networks achieve remarkable performances on a wide range of tasks with the aid of large-scale labeled datasets.
To mitigate the requirement for labeled data, self-training is widely used in both academia and industry by pseudo labeling on readily-available unlabeled data.
We propose Debiased, in which the generation and utilization of pseudo labels are decoupled by two independent heads.
arXiv Detail & Related papers (2022-02-15T02:14:33Z) - In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label
Selection Framework for Semi-Supervised Learning [53.1047775185362]
Pseudo-labeling (PL) is a general SSL approach that does not have this constraint but performs relatively poorly in its original formulation.
We argue that PL underperforms due to the erroneous high confidence predictions from poorly calibrated models.
We propose an uncertainty-aware pseudo-label selection (UPS) framework which improves pseudo labeling accuracy by drastically reducing the amount of noise encountered in the training process.
arXiv Detail & Related papers (2021-01-15T23:29:57Z) - Tackling Instance-Dependent Label Noise via a Universal Probabilistic
Model [80.91927573604438]
This paper proposes a simple yet universal probabilistic model, which explicitly relates noisy labels to their instances.
Experiments on datasets with both synthetic and real-world label noise verify that the proposed method yields significant improvements on robustness.
arXiv Detail & Related papers (2021-01-14T05:43:51Z)
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.