Uncertainty-Aware Boosted Ensembling in Multi-Modal Settings

TL;DR

This paper introduces an uncertainty-aware boosting method for multi-modal ensemble learning, improving robustness and calibration in healthcare applications involving speech and text data.

Contribution

It presents a novel boosting approach that emphasizes uncertain data points, enhancing multi-modal ensemble performance and robustness in real-world healthcare tasks.

Findings

Improved performance on Dementia and Parkinson's disease datasets

Reduced entropy and increased robustness to heteroscedasticity

Better calibration of modality-specific predictions

Abstract

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