mlsanityData to 7 Oct 2026

Uncertainty-Aware Boosted Ensembling in Multi-Modal Settings

arXiv 2104.10715 ↗First posted 21 Apr 2021cs.LG cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Reliability of machine learning (ML) systems is crucial in safety-critical applications such as healthcare, and uncertainty estimation is a widely researched method to highlight the confidence of ML systems in deployment. Sequential and parallel ensemble techniques have shown improved performance of ML systems in multi-modal settings by leveraging the feature sets together. We propose an uncertainty-aware boosting technique for multi-modal ensembling in order to focus on the data points with higher associated uncertainty estimates, rather than the ones with higher loss values. We evaluate this method on healthcare tasks related to Dementia and Parkinson's disease which involve real-world multi-modal speech and text data, wherein our method shows an improved performance. Additional analysis suggests that introducing uncertainty-awareness into the boosted ensembles decreases the overall entropy of the system, making it more robust to heteroscedasticity in the data, as well as better calibrating each of the modalities along with high quality prediction intervals. We open-source our entire codebase at https://github.com/usarawgi911/Uncertainty-aware-boosting

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 34 of its 64 references that are in the map. First posted on arXiv 21 Apr 2021.

Builds on

34 of 64 references.

References · 34

  1. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,120
  2. 2017On Calibration of Modern Neural Networkscited by 4,860
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  4. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  5. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  6. 2016Concrete Problems in AI Safetycited by 1,582
  7. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,345
  8. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
  9. 2017Multimodal Machine Learning: A Survey and Taxonomycited by 1,004
  10. 2017Deep Neural Networks as Gaussian Processescited by 617
  11. 2015Variational Dropout and the Local Reparameterization Trickcited by 489
  12. 2020Underspecification Presents Challenges for Credibility in Modern Machine Learningcited by 488
22 more
  1. 2019Verified Uncertainty Calibrationcited by 307
  2. 2015Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networkscited by 295
  3. 2020Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learningcited by 208
  4. 2017Active Bias: Training More Accurate Neural Networks by Emphasizing High Variance Samplescited by 147
  5. 2018High-Quality Prediction Intervals for Deep Learning: A Distribution-Free, Ensembled Approachcited by 117
  6. 2020Alzheimer's Dementia Recognition through Spontaneous Speech: The ADReSS Challengecited by 104
  7. 2018Uncertainty in Neural Networks: Approximately Bayesian Ensemblingcited by 94
  8. 2019Subspace Inference for Bayesian Deep Learningcited by 94
  9. 2019NGBoost: Natural Gradient Boosting for Probabilistic Predictioncited by 94
  10. 2020Uncertainty in Gradient Boosting via Ensemblescited by 56
  11. 2019r/Fakeddit: A New Multimodal Benchmark Dataset for Fine-grained Fake News Detectioncited by 53
  12. 2016On the Safety of Machine Learning: Cyber-Physical Systems, Decision Sciences, and Data Productscited by 52
  13. 2020To BERT or Not To BERT: Comparing Speech and Language-based Approaches for Alzheimer's Disease Detectioncited by 49
  14. 2013Confidence Intervals for Random Forests: The Jackknife and the Infinitesimal Jackknifecited by 43
  15. 2020Aleatoric and Epistemic Uncertainty with Random Forestscited by 42
  16. 2019Analyzing the Role of Model Uncertainty for Electronic Health Recordscited by 41
  17. 2019Maximizing Overall Diversity for Improved Uncertainty Estimates in Deep Ensemblescited by 30
  18. 2019Quantifying Point-Prediction Uncertainty in Neural Networks via Residual Estimation with an I/O Kernelcited by 19
  19. 2020Multimodal Inductive Transfer Learning for Detection of Alzheimer's Dementia and its Severitycited by 16
  20. 2020Comparing Natural Language Processing Techniques for Alzheimer's Dementia Prediction in Spontaneous Speechcited by 14
  21. 2019Building Calibrated Deep Models via Uncertainty Matching with Auxiliary Interval Predictorscited by 10
  22. 2020Why have a Unified Predictive Uncertainty? Disentangling it using Deep Split Ensemblescited by 5

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 2.

4 papers.

  1. 2022COLD Fusion: Calibrated and Ordinal Latent Distribution Fusion for Uncertainty-Aware Multimodal Emotion Recognitioncited by 22
  2. 2023Efficient Multimodal Neural Networks for Trigger-less Voice Assistantscited by 3
  3. 2022UATTA-ENS: Uncertainty Aware Test Time Augmented Ensemble for PIRC Diabetic Retinopathy Detectioncited by 0
  4. 2023UATTA-EB: Uncertainty-Aware Test-Time Augmented Ensemble of BERTs for Classifying Common Mental Illnesses on Social Media Postscited by 0