Uncertainty-Aware Boosted Ensembling in Multi-Modal Settings
This work addresses reliability in safety-critical healthcare applications by enhancing multi-modal ensembling, though it appears incremental as it builds on existing ensemble techniques with uncertainty integration.
The paper tackled the problem of improving reliability in multi-modal machine learning systems for healthcare by proposing an uncertainty-aware boosting technique that focuses on data points with higher uncertainty rather than higher loss, resulting in improved performance on Dementia and Parkinson's disease tasks using real-world speech and text data, with decreased system entropy and better calibration.
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