Soft-Label Training Preserves Epistemic Uncertainty

• URL: http://arxiv.org/abs/2511.14117v1
• Date: Tue, 18 Nov 2025 04:02:29 GMT
• Title: Soft-Label Training Preserves Epistemic Uncertainty
• Abstract summary: Machine learning tasks involve inherent subjectivity, where annotators naturally provide varied labels.<n>Standard practice collapses these label distributions into single labels, aggregating diverse human judgments into point estimates.<n>We argue that this approach is misaligned for ambiguous data--the annotation distribution itself should be regarded as the ground truth.
• Score: 4.2541480167286005
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Many machine learning tasks involve inherent subjectivity, where annotators naturally provide varied labels. Standard practice collapses these label distributions into single labels, aggregating diverse human judgments into point estimates. We argue that this approach is epistemically misaligned for ambiguous data--the annotation distribution itself should be regarded as the ground truth. Training on collapsed single labels forces models to express false confidence on fundamentally ambiguous cases, creating a misalignment between model certainty and the diversity of human perception. We demonstrate empirically that soft-label training, which treats annotation distributions as ground truth, preserves epistemic uncertainty. Across both vision and NLP tasks, soft-label training achieves 32% lower KL divergence from human annotations and 61% stronger correlation between model and annotation entropy, while matching the accuracy of hard-label training. Our work repositions annotation distributions from noisy signals to be aggregated away, to faithful representations of epistemic uncertainty that models should learn to reproduce.

Related papers

• DiCaP: Distribution-Calibrated Pseudo-labeling for Semi-Supervised Multi-Label Learning [83.94574004953346]
  Semi-supervised multi-label learning aims to leverage unlabeled data to improve the model's performance.<n>Most existing methods assign equal weights to all pseudo-labels regardless of their quality.<n>We propose Distribution-Calibrated Pseudo-labeling (DiCaP), a correctness-aware framework that estimates posterior precision to calibrate pseudo-label weights.
  arXiv  Detail & Related papers  (2025-11-25T11:55:02Z)
• Label Distribution Learning with Biased Annotations by Learning Multi-Label Representation [120.97262070068224]
  Multi-label learning (MLL) has gained attention for its ability to represent real-world data.<n>Label Distribution Learning (LDL) faces challenges in collecting accurate label distributions.
  arXiv  Detail & Related papers  (2025-02-03T09:04:03Z)
• Towards the Mitigation of Confirmation Bias in Semi-supervised Learning: a Debiased Training Perspective [6.164100243945264]
  Semi-supervised learning (SSL) commonly exhibits confirmation bias, where models disproportionately favor certain classes. We introduce TaMatch, a unified framework for debiased training in SSL. We show that TaMatch significantly outperforms existing state-of-the-art methods across a range of challenging image classification tasks.
  arXiv  Detail & Related papers  (2024-09-26T21:50:30Z)
• Retraining with Predicted Hard Labels Provably Increases Model Accuracy [77.71162068832108]
  Retraining can improve the population accuracy obtained by initially training with the given (noisy) labels.<n>We empirically show that retraining selectively on the samples for which the predicted label matches the given label significantly improves label DP training at no extra privacy cost.
  arXiv  Detail & Related papers  (2024-06-17T04:53:47Z)
• Self-Knowledge Distillation for Learning Ambiguity [11.755814660833549]
  Recent language models often over-confidently predict a single label without consideration for its correctness. We propose a novel self-knowledge distillation method that enables models to learn label distributions more accurately. We validate our method on diverse NLU benchmark datasets and the experimental results demonstrate its effectiveness in producing better label distributions.
  arXiv  Detail & Related papers  (2024-06-14T05:11:32Z)
• Perceptual Quality-based Model Training under Annotator Label Uncertainty [15.015925663078377]
  Annotators exhibit disagreement during data labeling, which can be termed as annotator label uncertainty. We introduce a novel perceptual quality-based model training framework to objectively generate multiple labels for model training.
  arXiv  Detail & Related papers  (2024-03-15T10:52:18Z)
• Learning with Complementary Labels Revisited: The Selected-Completely-at-Random Setting Is More Practical [66.57396042747706]
  Complementary-label learning is a weakly supervised learning problem. We propose a consistent approach that does not rely on the uniform distribution assumption. We find that complementary-label learning can be expressed as a set of negative-unlabeled binary classification problems.
  arXiv  Detail & Related papers  (2023-11-27T02:59:17Z)
• Probabilistic Test-Time Generalization by Variational Neighbor-Labeling [62.158807685159736]
  This paper strives for domain generalization, where models are trained exclusively on source domains before being deployed on unseen target domains. Probability pseudo-labeling of target samples to generalize the source-trained model to the target domain at test time. Variational neighbor labels that incorporate the information of neighboring target samples to generate more robust pseudo labels.
  arXiv  Detail & Related papers  (2023-07-08T18:58:08Z)
• 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)
• Uncertainty-aware Label Distribution Learning for Facial Expression Recognition [13.321770808076398]
  We propose a new uncertainty-aware label distribution learning method to improve the robustness of deep models against uncertainty and ambiguity. Our method can be easily integrated into a deep network to obtain more training supervision and improve recognition accuracy.
  arXiv  Detail & Related papers  (2022-09-21T15:48:41Z)
• Resolving label uncertainty with implicit posterior models [71.62113762278963]
  We propose a method for jointly inferring labels across a collection of data samples. By implicitly assuming the existence of a generative model for which a differentiable predictor is the posterior, we derive a training objective that allows learning under weak beliefs.
  arXiv  Detail & Related papers  (2022-02-28T18:09:44Z)
• Credal Self-Supervised Learning [0.0]
  We show how to let the learner generate "pseudo-supervision" for unlabeled instances. In combination with consistency regularization, pseudo-labeling has shown promising performance in various domains. We compare our methodology to state-of-the-art self-supervision approaches.
  arXiv  Detail & Related papers  (2021-06-22T15:19:04Z)
• Exploiting Sample Uncertainty for Domain Adaptive Person Re-Identification [137.9939571408506]
  We estimate and exploit the credibility of the assigned pseudo-label of each sample to alleviate the influence of noisy labels. Our uncertainty-guided optimization brings significant improvement and achieves the state-of-the-art performance on benchmark datasets.
  arXiv  Detail & Related papers  (2020-12-16T04:09:04Z)

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.