Abraham Chan, Arpan Gujarati, Karthik Pattabiraman and Sathish Gopalakrishnan. Proceedings of the IEEE/IFIP International Conference on Dependable Systems and Networks (DSN), 2025. (Acceptance Rate: 20.1%) [ PDF | Talk ] Artifacts available, reviewed and reproducible.
Abstract: Safety-critical domains, such as healthcare and autonomous vehicles, employ machine learning (ML), where mis-predictions can cause severe repercussions. Training datasets may contain faults, thereby compromising ML accuracy. Ensembles, where multiple ML models vote on predictions, are effective at maintaining predictive capability, and thus resilient against faulty training data because individual models focus on diverse input features. Nevertheless, ensemble diversity varies per input. Hence, weighted ensembles can bolster resilience by assigning unique weights to constituent models. While existing weighted ensembles
focus on output-space diversity, we propose leveraging their feature-space diversity to better capture model independence and achieve greater resilience. Therefore, we present ReMlX, which applies explainable artificial intelligence to extract the feature-space diversity of ensemble models, and adjusts their weights to maximize resilience. Compared to its most competitive baseline, ReMlX is 12% more resilient but 15% slower than dynamic weighted ensembles based on stacking.