Beyond the Mean: Modelling Annotation Distributions in Continuous Affect Prediction

• URL: http://arxiv.org/abs/2604.07198v1
• Date: Wed, 08 Apr 2026 15:26:56 GMT
• Title: Beyond the Mean: Modelling Annotation Distributions in Continuous Affect Prediction
• Abstract summary: We propose a distribution-aware framework that models annotation consensus using the Beta distribution.<n>Instead of predicting a single affect value, models estimate the mean and standard deviation of the annotation distribution.<n>As a result, the model captures not only the central tendency of emotional perception but also variability, asymmetry, and uncertainty in annotator responses.
• Score: 3.3187704612685267
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Emotion annotation is inherently subjective and cognitively demanding, producing signals that reflect diverse perceptions across annotators rather than a single ground truth. In continuous affect prediction, this variability is typically collapsed into point estimates such as the mean or median, discarding valuable information about annotator disagreement and uncertainty. In this work, we propose a distribution-aware framework that models annotation consensus using the Beta distribution. Instead of predicting a single affect value, models estimate the mean and standard deviation of the annotation distribution, which are transformed into valid Beta parameters through moment matching. This formulation enables the recovery of higher-order distributional descriptors, including skewness, kurtosis, and quantiles, in closed form. As a result, the model captures not only the central tendency of emotional perception but also variability, asymmetry, and uncertainty in annotator responses. We evaluate the proposed approach on the SEWA and RECOLA datasets using multimodal features. Experimental results show that Beta-based modelling produces predictive distributions that closely match the empirical annotator distributions while achieving competitive performance with conventional regression approaches. These findings highlight the importance of modelling annotation uncertainty in affective computing and demonstrate the potential of distribution-aware learning for subjective signal analysis.

Related papers

• A Multi-Dimensional Evaluation of Explainability in Media Bias Detection [10.798797986346914]
  We present a multi-dimensional evaluation of explainability in encoder-based media bias detection using the Bias s By Experts dataset.<n>We study BERT and RoBERTa as classifiers along three complementary axes: predictive performance, explanation plausibility, and mechanistic faithfulness.<n>Our findings suggest that predictive performance, attribution plausibility, and mechanistic faithfulness characterize different aspects of model behavior.
  arXiv  Detail & Related papers  (2026-07-22T09:29:49Z)
• Bridging Domain Expertise and Generalization for Performance Estimation [44.139948614374106]
  Performance estimation under distribution shift aims to predict how a model behaves on an unlabeled test set whose distribution differs from the training data.<n>Existing approaches rely solely on the outputs of the given model whose biases are amplified once the distribution shifts.<n>We propose Fused Reference Alignment Prediction (FRAP) to construct a more reliable surrogate of the ground-truth labels.
  arXiv  Detail & Related papers  (2026-06-04T16:10:04Z)
• Debiased Counterfactual Generation via Flow Matching from Observations [4.188178237487111]
  Estimating counterfactual distributions under interventions is central to treatment risk assessment and counterfactual generation tasks.<n>We show that under standard assumptions, observational and counterfactual outcome distributions are tightly linked.<n>These properties motivate learning counterfactual distributions not from scratch, but via a deconfounding flow from the observational distribution.
  arXiv  Detail & Related papers  (2026-05-08T12:35:21Z)
• Uncertainty Estimation using Variance-Gated Distributions [0.6340400318304492]
  We propose an intuitive framework for uncertainty estimation and decomposition based on the signal-to-noise ratio of class probability distributions.<n>We introduce a variance-gated measure that scales predictions by a confidence factor derived from ensembles.
  arXiv  Detail & Related papers  (2025-09-07T16:19:21Z)
• Beyond RMSE and MAE: Introducing EAUC to unmask hidden bias and unfairness in dyadic regression models [5.336076422485076]
  We show that non-uniform observed value distributions of individual entities lead to severe biases in state-of-the-art models.<n>We introduce Eccentricity-Area Under the Curve (EAUC) as a novel metric that can quantify it in all studied domains and models.
  arXiv  Detail & Related papers  (2024-01-19T13:41:08Z)
• Confidence and Dispersity Speak: Characterising Prediction Matrix for Unsupervised Accuracy Estimation [51.809741427975105]
  This work aims to assess how well a model performs under distribution shifts without using labels. We use the nuclear norm that has been shown to be effective in characterizing both properties. We show that the nuclear norm is more accurate and robust in accuracy than existing methods.
  arXiv  Detail & Related papers  (2023-02-02T13:30:48Z)
• The Implicit Delta Method [61.36121543728134]
  In this paper, we propose an alternative, the implicit delta method, which works by infinitesimally regularizing the training loss of uncertainty. We show that the change in the evaluation due to regularization is consistent for the variance of the evaluation estimator, even when the infinitesimal change is approximated by a finite difference.
  arXiv  Detail & Related papers  (2022-11-11T19:34:17Z)
• End-to-End Label Uncertainty Modeling in Speech Emotion Recognition using Bayesian Neural Networks and Label Distribution Learning [0.0]
  We propose an end-to-end Bayesian neural network capable of being trained on a distribution of annotations to capture the subjectivity-based label uncertainty. We show that the proposed t-distribution based approach achieves state-of-the-art uncertainty modeling results in speech emotion recognition.
  arXiv  Detail & Related papers  (2022-09-30T12:55:43Z)
• Label Uncertainty Modeling and Prediction for Speech Emotion Recognition using t-Distributions [15.16865739526702]
  We propose to model the label distribution using a Student's t-distribution. We derive the corresponding Kullback-Leibler divergence based loss function and use it to train an estimator for the distribution of emotion labels. Results reveal that our t-distribution based approach improves over the Gaussian approach with state-of-the-art uncertainty modeling results.
  arXiv  Detail & Related papers  (2022-07-25T12:38:20Z)
• Predicting with Confidence on Unseen Distributions [90.68414180153897]
  We connect domain adaptation and predictive uncertainty literature to predict model accuracy on challenging unseen distributions. We find that the difference of confidences (DoC) of a classifier's predictions successfully estimates the classifier's performance change over a variety of shifts. We specifically investigate the distinction between synthetic and natural distribution shifts and observe that despite its simplicity DoC consistently outperforms other quantifications of distributional difference.
  arXiv  Detail & Related papers  (2021-07-07T15:50:18Z)
• Latent Causal Invariant Model [128.7508609492542]
  Current supervised learning can learn spurious correlation during the data-fitting process. We propose a Latent Causal Invariance Model (LaCIM) which pursues causal prediction.
  arXiv  Detail & Related papers  (2020-11-04T10:00:27Z)
• Unlabelled Data Improves Bayesian Uncertainty Calibration under Covariate Shift [100.52588638477862]
  We develop an approximate Bayesian inference scheme based on posterior regularisation. We demonstrate the utility of our method in the context of transferring prognostic models of prostate cancer across globally diverse populations.
  arXiv  Detail & Related papers  (2020-06-26T13:50:19Z)
• Decision-Making with Auto-Encoding Variational Bayes [71.44735417472043]
  We show that a posterior approximation distinct from the variational distribution should be used for making decisions. Motivated by these theoretical results, we propose learning several approximate proposals for the best model. In addition to toy examples, we present a full-fledged case study of single-cell RNA sequencing.
  arXiv  Detail & Related papers  (2020-02-17T19:23:36Z)

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.