Arthur Hoarau
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Arthur Hoarau has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Benjamin Quost
UMR CNRS 7253 Heudiasyc, Université de technologie de Compiègne, Compiègne, France
1 shared publication Chenrui Zhu
Université de Technologie de Compiègne
1 shared publicationLouenas Bounia
Université de Technologie de Compiègne
1 shared publicationSébastien Destercke
Université de Technologie de Compiègne
1 shared publication- Sébastien Destercke
Université de Technologie de Compiègne
1 shared publication Vu-Linh Nguyen
Université de Technologie de Compiègne
1 shared publication
Latest Publications
- 3 August 2026
- Published by Springer Nature
- p. 204-219
Robust Explanations Through Uncertainty Decomposition: A Path to Trustworthier AI
- 3 August 2026
- Published by Springer Nature
- p. 204-219
Robust Explanations Through Uncertainty Decomposition: A Path to Trustworthier AI
- Open Access
- 9 May 2026
- Published by Springer Nature in Machine Learning
- Vol. 115 (5) , 121
Reducing Aleatoric and Epistemic Uncertainty Through Multi-modal Data Acquisition
To generate accurate and reliable predictions, modern AI systems need to combine data from multiple modalities, such as text, images, audio, spreadsheets, and time series. However, collecting training and test data for many modalities is challenging and time-consuming, creating a need for cost-efficient multi-modal data acquisition. In this paper we advocate that this can be realized by disentangling epistemic and aleatoric uncertainty. It is commonly assumed in the machine learning community that epistemic uncertainty can be reduced by collecting more data, while aleatoric uncertainty is irreducible. We claim that this assumption can be challenged in modern multi-modal AI systems, and we introduces an innovative data acquisition framework where uncertainty disentanglement leads to actionable decisions, allowing cost-efficient sampling in two directions: sample size and data modality. The main hypothesis is that aleatoric uncertainty decreases as the number of modalities increases, while epistemic uncertainty decreases by collecting more observations. We provide a theoretical analysis and proof-of-concept implementations on various multi-modal datasets to prove the usefulness of our framework, which combines ideas from active learning, active feature acquisition and uncertainty quantification.
- 9 May 2026
- Published by Springer Nature in Machine Learning
- Vol. 115 (5) , 121
Open AccessReducing Aleatoric and Epistemic Uncertainty Through Multi-modal Data Acquisition
To generate accurate and reliable predictions, modern AI systems need to combine data from multiple modalities, such as text, images, audio, spreadsheets, and time series. However, collecting training and test data for many modalities is challenging and time-consuming, creating a need for cost-efficient multi-modal data acquisition. In this paper we advocate that this can be realized by disentangling epistemic and aleatoric uncertainty. It is commonly assumed in the machine learning community that epistemic uncertainty can be reduced by collecting more data, while aleatoric uncertainty is irreducible. We claim that this assumption can be challenged in modern multi-modal AI systems, and we introduces an innovative data acquisition framework where uncertainty disentanglement leads to actionable decisions, allowing cost-efficient sampling in two directions: sample size and data modality. The main hypothesis is that aleatoric uncertainty decreases as the number of modalities increases, while epistemic uncertainty decreases by collecting more observations. We provide a theoretical analysis and proof-of-concept implementations on various multi-modal datasets to prove the usefulness of our framework, which combines ideas from active learning, active feature acquisition and uncertainty quantification.