Prediction Uncertainty

Prediction uncertainty, the quantification of confidence in a model's predictions, is a crucial area of research aiming to improve the reliability and trustworthiness of machine learning models across diverse applications. Current efforts focus on developing methods to accurately estimate uncertainty, employing techniques like Bayesian neural networks, deep ensembles, and conformal prediction, often tailored to specific model architectures (e.g., recurrent neural networks, transformers) and data types (e.g., time series, images). This research is vital for enhancing decision-making in high-stakes domains such as healthcare, autonomous driving, and weather forecasting, where understanding the limitations of predictions is paramount for safety and effective resource allocation. Furthermore, research is actively exploring how to incorporate and propagate uncertainty from various sources, including input data, model parameters, and the inherent randomness in the data itself.

Papers

December 18, 2023

Uncertainty-based Fairness Measures
Selim Kuzucu, Jiaee Cheong, Hatice Gunes, Sinan Kalkan
Prediction Uncertainty Fairness Measure Biased Prediction Uncertainty Aware Fairness

December 11, 2023

Uncertainty quantification in automated valuation models with locally weighted conformal prediction
Anders Hjort, Gudmund Horn Hermansen, Johan Pensar, Jonathan P. Williams
Uncertainty Quantification Conformal Prediction Prediction Uncertainty Valuation Model Non Parametric Learning Confidence Set

October 25, 2023

SMURF-THP: Score Matching-based UnceRtainty quantiFication for Transformer Hawkes Process
Zichong Li, Yanbo Xu, Simiao Zuo, Haoming Jiang, Chao Zhang, Tuo Zhao, Hongyuan Zha
Uncertainty Quantification Performance Score Hawkes Process Prediction Uncertainty Event Prediction Event Sequence Data Transformer Hawkes Process

October 18, 2023

Can bin-wise scaling improve consistency and adaptivity of prediction uncertainty for machine learning regression ?
Pascal Pernot
Loss Function Adaptive Importance Strong Consistency Prediction Uncertainty Machine Learning Regression Binning Method Isotonic Regression

October 9, 2023

Quantifying Uncertainty in Deep Learning Classification with Noise in Discrete Inputs for Risk-Based Decision Making
Maryam Kheirandish, Shengfan Zhang, Donald G. Catanzaro, Valeriu Crudu
Uncertainty Quantification Industrial Disturbing Noise Risk Prediction Bayesian Deep Learning Prediction Uncertainty Deep Learning Classification Risk Based Decision

October 5, 2023

Sparse Deep Learning for Time Series Data: Theory and Applications
Mingxuan Zhang, Yan Sun, Faming Liang
Financial Application Recurrent Neural Network Theoretical Understanding Many Sparse Autoregressive Model Time Series Data Prediction Uncertainty Sparse Deep

September 19, 2023

Uncertainty Estimation in Instance Segmentation with Star-convex Shapes
Qasim M. K. Siddiqui, Sebastian Starke, Peter Steinbach
Instance Segmentation Uncertainty Estimation Convex Set Prediction Uncertainty Uncertainty Score

September 14, 2023

Flexible Visual Recognition by Evidential Modeling of Confusion and Ignorance
Lei Fan, Bo Liu, Haoxiang Li, Ying Wu, Gang Hua
Visual Recognition Prediction Uncertainty Evidential Model Class Uncertainty Cell Phone Recognition

July 7, 2023

DE-TGN: Uncertainty-Aware Human Motion Forecasting using Deep Ensembles
Kareem A. Eltouny, Wansong Liu, Sibo Tian, Minghui Zheng, Xiao Liang
Deep Ensemble Motion Capture Prediction Uncertainty Temporal Graph Network Human Motion Forecasting Future Human Pose

June 13, 2023

LMD: Light-weight Prediction Quality Estimation for Object Detection in Lidar Point Clouds
Tobias Riedlinger, Marius Schubert, Sarina Penquitt, Jan-Marcel Kezmann, Pascal Colling, Karsten Kahl, Lutz Roese-Koerner, Michael Arnold, Urs Zimmermann, Matthias Rottmann
LiDAR Point Cloud Prediction Uncertainty Lidar Point Cloud Data

May 15, 2023

Integrating Uncertainty into Neural Network-based Speech Enhancement
Huajian Fang, Dennis Becker, Stefan Wermter, Timo Gerkmann
Uncertainty Estimation Neural Topic Prediction Uncertainty Clean Speech Neural Speech Enhancement Speech Enhancement Network Mask Estimation Module

April 10, 2023

Gradient-based Uncertainty Attribution for Explainable Bayesian Deep Learning
Hanjing Wang, Dhiraj Joshi, Shiqiang Wang, Qiang Ji
Uncertainty Quantification Gradient Based Prediction Uncertainty Explainable Deep Learning Uncertainty Mitigation

March 20, 2023

Uncertainty-aware deep learning for digital twin-driven monitoring: Application to fault detection in power lines
Laya Das, Blazhe Gjorgiev, Giovanni Sansavini
Deep Learning Deep Neural Network Data Detection Digital Twin Uncertainty Aware Prediction Uncertainty Parameter Uncertainty Power Line Deep Neural Network Parameter Uncertainty Aware Model

March 16, 2023

Adaptive Modeling of Uncertainties for Traffic Forecasting
Ying Wu, Yongchao Ye, Adnan Zeb, James J. Q. Yu, Zheng Wang
Traffic Prediction Traffic Forecasting High Uncertainty Value Prediction Uncertainty Adaptive Model

February 2, 2023

Benchmarking Probabilistic Deep Learning Methods for License Plate Recognition
Franziska Schirrmacher, Benedikt Lorch, Anatol Maier, Christian Riess
Uncertainty Quantification License Plate Prediction Uncertainty Recognition Performance Distribution Image Probabilistic Deep Learning

January 18, 2023

Adaptively Integrated Knowledge Distillation and Prediction Uncertainty for Continual Learning
Kanghao Chen, Sijia Liu, Ruixuan Wang, Wei-Shi Zheng
Knowledge Distillation Continual LEArning Catastrophic Forgetting Prediction Uncertainty Stability Plasticity

December 14, 2022

Interactive Concept Bottleneck Models
Kushal Chauhan, Rishabh Tiwari, Jan Freyberg, Pradeep Shenoy, Krishnamurthy Dvijotham
Concept Bottleneck Model Prediction Uncertainty Interpretable Concept Prediction Task Concept Prediction

December 1, 2022

Deep Kernel Learning for Mortality Prediction in the Face of Temporal Shift
Miguel Rios, Ameen Abu-Hanna
Human Face Neural Model Prediction Uncertainty Temporal Shift Neural Network Baseline Mortality Prediction Overconfident Prediction Deep Kernel Learning

November 3, 2022

Conformal Prediction for STL Runtime Verification
Lars Lindemann, Xin Qin, Jyotirmoy V. Deshmukh, George J. Pappas
Conformal Prediction Cyber Physical System Prediction Uncertainty Runtime Verification

September 29, 2022

Bayesian Neural Network Versus Ex-Post Calibration For Prediction Uncertainty
Satya Borgohain, Klaus Ackermann, Ruben Loaiza-Maya
Bayesian Neural Network Predictive Uncertainty Prediction Uncertainty Predictive Distribution Probabilistic Neural Network