Deep Ensembles

Follow this topic Ask about this topic

A deep ensemble trains several neural networks—often with different initializations, architectures, data views, or training trajectories—and averages their predictions. The spread among members can estimate uncertainty, helping flag ambiguous or out-of-distribution cases, while averaging can improve accuracy and calibration. Approaches range from independently trained models and specialist ensembles to snapshot, shared-backbone, last-layer, and Bayesian-weighted variants that aim to reduce computational costs. A central challenge is that diversity is expensive and disagreement is not automatically reliable: performance can vary by task or degrade under domain shift, so evaluation must assess both uncertainty ranking and calibration.

Latest papers

54 papers4 papers in the last four weeks, down 33% on the four weeks before. 0.0% of all new papers.

Ranked Right, Sized Wrong: Ensemble Spread Fails Silently at Streamflow Extremes
Oct 14, 2026Justin Gallant, Tyler WilsonStreamflow Forecasting Uncertainty Quantification
University of British Columbia, Vancouver, BC, Canada
Compact set-valued deep ensembling in multi-class classification
Oct 4, 2026Kim-Dung Tran, Dang-Man Nguyen, Vu-Linh Nguyen +3Deep Ensembles Multiclass Classification
UMR CNRS 7253, Heudiasyc, Universit´e de Technologie de Compi`egne, Compi`egne, France. · School of Knowledge Science, Japan Advanced Institute of Science and Technology, Nomi, Japan.
Does Neural Complexity Improve Health Misinformation Detection? A Leakage-Controlled Cross-Corpus Benchmark
Oct 3, 2026Mkululi SIKOSANAHealth Misinformation Detection Fake News Detection
Department of Computing and Mathematics, Manchester Metropolitan University Manchester M15 6BH, United Kingdom
Calibrated Uncertainty for Informative Path Planning in Aquatic Environmental Monitoring
Sep 28, 2026Samuel Yanes Luis, Alejandro Casado Pérez, Alejandro Mendoza Barrionuevo +3Informative Path Planning Deep Ensembles
Department of Electronic Technology, University of Sevilla, Sevilla, Spain · Department of Electronic Engineering, University of Sevilla, Sevilla, Spain
Metacognitive Selective Ensemble for Mobile Systems
Sep 25, 2026Sungmin Lee, Kichang Lee, Joonhee Lee +3Ensemble Learning Deep Ensembles
Yonsei University · Dankook University
Super-Resolution of Solar Magnetograms via Adaptive Stratified Ensemble Learning with Uncertainty Estimation
Sep 22, 2026Sina Norouzi Kandalan, Haodi Jiang, Jason T. L. Wang +1Solar Physics Deep Ensembles
Department of Computer Science, Sam Houston State University, Huntsville, TX 77341, USA · Department of Computer Science, New Jersey Institute of Technology, Newark, NJ 07102, USA · Department of Physics, New Jersey Institute of Technology, Newark, NJ 07102, USA
CORE-STACK+: Meta-Learning for Deep Stacked Generalization
Sep 22, 2026Noor Islam S. MohammadEnsemble Learning Meta-Learning
Department of Computer Science Istanbul Technical University Maslak, Istanbul 34469, TR
Virtual neural networks: hundreds of souls in a body
Sep 21, 2026Petr Hurtik, Marek Vajgl, Zahra Alijani +1Neural Network Robustness Deep Ensembles
Centre of Excellence IT4Innovations, Institute for Research and Applications of Fuzzy Modeling, University of Ostrava, 30. dubna 22, Ostrava, Czech Republic
A Distributional Optimisation Perspective on Combining Models in Deep Learning
Sep 21, 2026Congye Wang, Yan Lin, Zheyang Shen +2Ensemble Learning Deep Ensembles
Newcastle University, UK
Attention-Enhanced Deep Features with Heterogeneous Ensemble Learning for Glaucoma Detection
Sep 6, 2026Abdullah Al Shafi, Nishat Sadaf Lira, Abrar Hasan +2Glaucoma Detection Ensemble Learning
Department of CSE, Khulna University of Engineering & Technology, Bangladesh · Department of CSE, Daffodil International University, Bangladesh · Department of SWE, Green University of Bangladesh
Reliability analysis for BraTS-GoAT segmentation: a controlled robustness study of deep-ensemble uncertainty
Aug 13, 2026Riya Deepak Shet, Chenxi Liang, Le ZhangUncertainty Quantification Neural Network Robustness
Department of Cancer and Genomic Sciences, School of Medical Sciences, College of Medicine and Health, University of Birmingham, Birmingham, United Kingdom
Uncertainty-Aware Deep Learning for Genomics Applications: Insights from an Empirical Study
Aug 11, 2026Sepideh Saran, Mahsa Ghanbari, Uwe OhlerBayesian Neural Networks Uncertainty Quantification
The Berlin Institute for Medical Systems Biology, Max Delbrück Center for Molecular Medicine, Germany · Department of Electrical Engineering and Computer Science, Technical University of Berlin, Germany · Department of Biology, Humboldt University of Berlin, Germany +1
Uncertainty-Aware and Explainable Ensemble Deep Learning Framework for Multi-Class Skin Lesion Classification
Aug 11, 2026Rofiqul Islam, Lilatul FerdouseSkin Lesion Classification Deep Ensembles
Department of Computer Science and Physics, Wilfrid Laurier University, Waterloo, ON, Canada
Dense-Cast: A lightweight ensemble of deep learning architectures for precipitation nowcasting
Aug 6, 2026Gourav Jyoti Kalita, Hidam Kumarjit SinghPrecipitation Forecasting Deep Ensembles
Department of Electronics and Communication Technology, Gauhati University, Guwahati-781014, Assam, India
Multi-Backbone Self-Supervised Ensembles for Audio Deepfake Detection and a Cross-Track Analysis of Generation-Detection Asymmetry
Aug 3, 2026Seunghyun Kim, Junghyun Kim, Jiyoung WooAudio Deepfake Detection Deep Ensembles
Soonchunhyang University, Department of AI and Big Data Engineering, Asan, Republic of Korea
ST-LoRA: Single Trajectory LoRA Ensemble for Uncertainty Aware Agricultural Segmentation
Aug 2, 2026Mohamed Farag, Genc Hoxha, Yahia Maleki +2Image Segmentation Ensemble Learning
Machine Learning in Agriculture Lab, Institute of Geodesy and Geoinformation, University of Bonn, Bonn, Germany · Commonwealth Scientific and Industrial Research Organisation (CSIRO), Australia · Lamarr Institute for Machine Learning and Artificial Intelligence, University of Bonn, Bonn, Germany
Uncertainty quantification for trustworthy deep learning: Methods and measures
Jul 30, 2026H. Martin Gillis, Thomas TrappenbergBayesian Neural Networks Uncertainty Quantification
Faculty of Computer Science, Dalhousie University, Halifax, Nova Scotia, Canada
Covariance Last-Layer Ensembles: Function-Space Diversity for Efficient Uncertainty Quantification
Jul 26, 2026H. Martin Gillis, Isaac Xu, Gabriel Spadon +1Uncertainty Quantification Ensemble Learning
Dalhousie University Halifax, Nova Scotia, Canada
Calibrated Selective Prediction Using Deep Ensembles for ROI-Based Thyroid Nodule Ultrasound Classification Under Dataset Shift: A Retrospective Evaluation
Jul 13, 2026Md. Sadibul Hasan Sadib, Md. Mohayminul Mukit, Rahmatul Kabir Rasel Sarker +2Probability Calibration Selective Prediction
Department of Computer Science and Engineering, Daffodil International University, Dhaka, Bangladesh. · Department of Public Health, Daffodil International University, Dhaka, Bangladesh. · Faculty of Health, Education and Life Sciences, Birmingham City University, Birmingham, United Kingdom.
Ensemble Deep Learning Approaches for AI-Altered Video Detection
Jul 8, 2026Laiba Khan, Hung-Mao Wu, Wei Lin +3Multimodal Deepfake Detection Deep Ensembles
Department of Mathematical and Computational Sciences, University of Toronto Mississauga · Department of Mathematical and Computational Sciences, University of Toronto
Efficient Bayesian Deep Ensembles via Analytic Predictive Inference
Jul 7, 2026Sina Aghaee Dabaghan Fard, Marie Maros, Jaesung LeeUncertainty Quantification Interpretable ML
Wm Michael Barnes ’64 Department of Industrial and Systems Engineering Texas A&M University College Station, TX, USA
Beyond Modality Fusion: Deep Ensembles for Multimodal Classification
Jul 6, 2026Ilya Burenko, Dmitry VetrovModality Imbalance Multimodal Classification
ScaDS.AI, Technische Universität Dresden · Dresden, Germany · Constructor University +1
PulmoSight-XAI: An Explainable Multi-View Attention Ensemble with Gradient Boosting Meta-Learning for Multi-Label Chest X-Ray Classification
Jul 5, 2026Moshiur Rahman, Shafqat Alam, Tasnia Binte MamunClass-Imbalanced Learning Chest X-Ray Classification
Department of Biomedical Engineering Bangladesh University of Engineering and Technology (BUET), Dhaka, Bangladesh
Von Mises Based Uncertainty Quantification for Closely Spaced Automotive Radar Targets
Jun 30, 2026Vinay Kulkarni, V. V. ReddyEvidential Deep Learning Uncertainty Quantification
International Institute of Information Technology, Bengaluru, India
Uncertainty Estimation in Pathology Foundation Models via Deep Mutual Learning
Jun 29, 2026Gbègninougbo Aurel Davy Tchokponhoue, Sevda Öğüt, Ali Idri +2Pathology Foundation Models Deep Ensembles
EPFL, Lausanne, Switzerland · UM5, Rabat, Morocco
Technical Report for the ICRA 2026 GOOSE 2D Fine-Grained Semantic Segmentation Challenge: Pretraining-Diverse Ensemble of Foundation Vision Encoders for Robust Outdoor Scene Understanding
Jun 22, 2026Boyan Wang, Yongxi Huang, Wenjing Li +4Vision Foundation Model Adaptation Deep Ensembles
LION Lab, Hefei University of Technology, Hefei, China. · University of Macau, Macau, China.
Deep Temporal Modeling and Ensemble Fusion for Multimodal Emotion Recognition from Physiological Signals
Jun 12, 2026Desta Haileselassie Hagos, Saurav Keshari Aryal, Patrick Ymele-Leki +2Temporal Convolutional Networks Deep Ensembles
Howard University Washington, DC, USA
CEAR: Certified Ensemble Adversarial Robustness in DNNs
May 31, 2026Daniel Sadig, Mohammadreza Maleki, Hamed Karimi +1Neural Network Robustness Adversarial Robustness
Department of Electrical, Computer, and Biomedical Engineering, Toronto Metropolitan University, Toronto, ON, Canada · Vector Institute, Toronto, ON, Canada
DENSER: Depth-Guided Ensemble with Staged EFA-GS Reconstruction for Soccer Novel View Synthesis
May 31, 2026Parthsarthi Rawat3D Gaussian Splatting Novel View Synthesis
GameChanger by Dick’s Sporting Goods
Kalimati Vegetable Price Index Forecasting with a Momentum Corrected Online Stacking Ensemble
May 29, 2026Sahaj Raj MallaLong-Term Time Series Forecasting Time Series Forecasting
Department of Mathematics, Kathmandu University, Dhulikhel, Nepal

Oct 14, 2026J/K move · Enter open · S save

Ranked Right, Sized Wrong: Ensemble Spread Fails Silently at Streamflow Extremes

Justin Gallant, Tyler Wilson

University of British Columbia, Vancouver, BC, Canada

Streamflow Forecasting Uncertainty Quantification Uncertainty Calibration Time Series Forecasting Deep Ensembles

Open paper AskPDF arXiv

Deep learning models, particularly Long Short-Term Memory networks, are increasingly used for operational streamflow forecasting, with ensemble spread providing a signal of predictive uncertainty. As climate change increases the frequency of hydroclimatic extremes, these models will increasingly operate under flow conditions that are rare in their historical records. We therefore evaluate whether ensemble spread remains informative under increasing flows, examining both its magnitude relative to error and its ability to rank errors. Prediction error is approximately

2\times

the corrected spread at ordinary flows and up to

4\times

at the highest flows, with the discrepancy increasing with flow (log-log slope

1.30

, 95% CI:

[1.20,1.41]

). Under-dispersion is strongest in observed extreme flows beyond the training record, reaching an

18\times

discrepancy. This is pervasive and not explainable by conditional mean bias. Area Under the Sparsification Error, a standard distribution-free metric of uncertainty ranking, describing how well a model knows when it is uncertain, indicates near-oracle ranking for ensemble spread (

0.071

), yet ordering by predicted discharge alone nearly matches it. Informative uncertainty ranking can coexist with severe under-dispersion. In deployment, error ranking cannot be verified, yet the spread is available, and it is relied on as the uncertainty signal under increasingly extreme conditions, while systematically understating risk, most severely for the extreme events that matter most.