Confidence-Aware Calibration and Scoring Functions for Curriculum Learning

• URL: http://arxiv.org/abs/2301.12589v1
• Date: Sun, 29 Jan 2023 23:59:40 GMT
• Title: Confidence-Aware Calibration and Scoring Functions for Curriculum Learning
• Authors: Shuang Ao, Stefan Rueger, Advaith Siddharthan
• Abstract summary: We integrate notions of model confidence and human confidence with label smoothing to achieve better model calibration and generalization. A higher model or human confidence score indicates a more recognisable and therefore easier sample, and can therefore be used as a scoring function to rank samples in curriculum learning.
• Score: 1.192436948211501
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite the great success of state-of-the-art deep neural networks, several studies have reported models to be over-confident in predictions, indicating miscalibration. Label Smoothing has been proposed as a solution to the over-confidence problem and works by softening hard targets during training, typically by distributing part of the probability mass from a `one-hot' label uniformly to all other labels. However, neither model nor human confidence in a label are likely to be uniformly distributed in this manner, with some labels more likely to be confused than others. In this paper we integrate notions of model confidence and human confidence with label smoothing, respectively \textit{Model Confidence LS} and \textit{Human Confidence LS}, to achieve better model calibration and generalization. To enhance model generalization, we show how our model and human confidence scores can be successfully applied to curriculum learning, a training strategy inspired by learning of `easier to harder' tasks. A higher model or human confidence score indicates a more recognisable and therefore easier sample, and can therefore be used as a scoring function to rank samples in curriculum learning. We evaluate our proposed methods with four state-of-the-art architectures for image and text classification task, using datasets with multi-rater label annotations by humans. We report that integrating model or human confidence information in label smoothing and curriculum learning improves both model performance and model calibration. The code are available at \url{https://github.com/AoShuang92/Confidence_Calibration_CL}.

Related papers

• Pre-Trained Vision-Language Models as Partial Annotators [40.89255396643592]
  Pre-trained vision-language models learn massive data to model unified representations of images and natural languages. In this paper, we investigate a novel "pre-trained annotating - weakly-supervised learning" paradigm for pre-trained model application and experiment on image classification tasks.
  arXiv  Detail & Related papers  (2024-05-23T17:17:27Z)
• 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)
• Self-Evolution Learning for Mixup: Enhance Data Augmentation on Few-Shot Text Classification Tasks [75.42002070547267]
  We propose a self evolution learning (SE) based mixup approach for data augmentation in text classification. We introduce a novel instance specific label smoothing approach, which linearly interpolates the model's output and one hot labels of the original samples to generate new soft for label mixing up.
  arXiv  Detail & Related papers  (2023-05-22T23:43:23Z)
• A Confidence-based Partial Label Learning Model for Crowd-Annotated Named Entity Recognition [74.79785063365289]
  Existing models for named entity recognition (NER) are mainly based on large-scale labeled datasets. We propose a Confidence-based Partial Label Learning (CPLL) method to integrate the prior confidence (given by annotators) and posterior confidences (learned by models) for crowd-annotated NER.
  arXiv  Detail & Related papers  (2023-05-21T15:31:23Z)
• 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)
• How Does Beam Search improve Span-Level Confidence Estimation in Generative Sequence Labeling? [11.481435098152893]
  This paper aims to provide some empirical insights on estimating model confidence for generative sequence labeling. As verified over six public datasets, we show that our proposed approach significantly reduces calibration errors of the predictions of a generative sequence labeling model.
  arXiv  Detail & Related papers  (2022-12-21T05:01:01Z)
• Going Beyond One-Hot Encoding in Classification: Can Human Uncertainty Improve Model Performance? [14.610038284393166]
  We show that label uncertainty is explicitly embedded into the training process via distributional labels. The incorporation of label uncertainty helps the model to generalize better to unseen data and increases model performance. Similar to existing calibration methods, the distributional labels lead to better-calibrated probabilities, which in turn yield more certain and trustworthy predictions.
  arXiv  Detail & Related papers  (2022-05-30T17:19:11Z)
• Semi-Supervised Learning of Semantic Correspondence with Pseudo-Labels [26.542718087103665]
  SemiMatch is a semi-supervised solution for establishing dense correspondences across semantically similar images. Our framework generates the pseudo-labels using the model's prediction itself between source and weakly-augmented target, and uses pseudo-labels to learn the model again between source and strongly-augmented target. In experiments, SemiMatch achieves state-of-the-art performance on various benchmarks, especially on PF-Willow by a large margin.
  arXiv  Detail & Related papers  (2022-03-30T03:52:50Z)
• Uncertainty-aware Self-training for Text Classification with Few Labels [54.13279574908808]
  We study self-training as one of the earliest semi-supervised learning approaches to reduce the annotation bottleneck. We propose an approach to improve self-training by incorporating uncertainty estimates of the underlying neural network. We show our methods leveraging only 20-30 labeled samples per class for each task for training and for validation can perform within 3% of fully supervised pre-trained language models.
  arXiv  Detail & Related papers  (2020-06-27T08:13:58Z)
• Meta-Learned Confidence for Few-shot Learning [60.6086305523402]
  A popular transductive inference technique for few-shot metric-based approaches, is to update the prototype of each class with the mean of the most confident query examples. We propose to meta-learn the confidence for each query sample, to assign optimal weights to unlabeled queries. We validate our few-shot learning model with meta-learned confidence on four benchmark datasets.
  arXiv  Detail & Related papers  (2020-02-27T10:22:17Z)
• FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence [93.91751021370638]
  Semi-supervised learning (SSL) provides an effective means of leveraging unlabeled data to improve a model's performance. In this paper, we demonstrate the power of a simple combination of two common SSL methods: consistency regularization and pseudo-labeling. Our algorithm, FixMatch, first generates pseudo-labels using the model's predictions on weakly-augmented unlabeled images.
  arXiv  Detail & Related papers  (2020-01-21T18:32:27Z)

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.