Fairness through Aleatoric Uncertainty [PDF]
Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, 2023 We propose a simple yet effective solution to tackle the often-competing goals of fairness and utility in classification tasks. While fairness ensures that the model's predictions are unbiased and do not discriminate against any particular group or individual, utility focuses on maximizing the model's predictive performance.
Anique Tahir +2 more
openaire +4 more sources
Uncertainty-Calibrated Collaborative Filtering via Heteroscedastic Bayesian Neural Networks [PDF]
EntropyAlthough recommendation systems based on neural collaborative filtering (NCF) can achieve high rating accuracy, the point estimates they generate do not express prediction confidence.
Xiaowei Wang
doaj +2 more sources
Benchmarking the performance of uncertainty quantification methods for neural network-based interatomic potentials [PDF]
Journal of CheminformaticsMachine-learned interatomic potentials (ML-IAPs) continue to gain popularity as accurate, computationally efficient replacements for traditional, physics-based interatomic potentials and expensive ab initio methods.
Nicholas T. Wimer +3 more
doaj +2 more sources
MIXED PROBABILITY MODELS FOR ALEATORIC UNCERTAINTY ESTIMATION IN THE CONTEXT OF DENSE STEREO MATCHING [PDF]
ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2021 The ability to identify erroneous depth estimates is of fundamental interest. Information regarding the aleatoric uncertainty of depth estimates can be, for example, used to support the process of depth reconstruction itself.
Z. Zhong, M. Mehltretter
doaj +3 more sources
Data-driven organic solubility prediction at the limit of aleatoric uncertainty [PDF]
Nature CommunicationsSmall molecule solubility is a critically important property which affects the efficiency, environmental impact, and phase behavior of synthetic processes.
Lucas Attia +3 more
doaj +2 more sources
Cyber Defense Effectiveness Evaluation for ICS Under Uncertainty: A Dynamic Bayesian Network Approach with Information Entropy [PDF]
EntropyProactive defense planning in Industrial Control Systems (ICS) is critically constrained by two intertwined types of uncertainty: epistemic uncertainty, arising from the defender’s limited observability of the system state and incomplete knowledge of ...
Rongbao Kang +6 more
doaj +2 more sources
UbiQTree: Uncertainty quantification in XAI with tree ensembles [PDF]
PatternsSummary: Explainable artificial intelligence (XAI) techniques, particularly Shapley additive explanations (SHAP), are essential for interpreting ensemble tree-based models in critical areas such as healthcare.
Akshat Dubey +3 more
doaj +2 more sources
Towards a more reliable assessment of aortic diameters using a Bayesian Z-score [PDF]
Scientific ReportsThe Z-score is a conceptually simple and widely adopted standard for assessing aortic dilatation from echocardiographic measurements. It is routinely used to monitor patient progression and schedule follow-up checks. However, several criticisms have been
Luca Bindini +7 more
doaj +2 more sources
JOINT ESTIMATION OF DEPTH AND ITS UNCERTAINTY FROM STEREO IMAGES USING BAYESIAN DEEP LEARNING [PDF]
ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2022 The necessity to identify errors in the context of image-based 3D reconstruction has motivated the development of various methods for the estimation of uncertainty associated with depth estimates in recent years.
M. Mehltretter
doaj +1 more source
Bayesian losses for homoscedastic aleatoric uncertainty modeling in pollen image detection [PDF]
Научно-технический вестник информационных технологий, механики и оптики, 2021 The paper investigates the homoscedastic aleatoric uncertainty modeling for the detection of pollen in images. The new uncertainty modeling loss functions are presented, which are based on the focal and smooth L1 losses.
Natalia E. Khanzhina
doaj +1 more source