# PB-OEL: A Performance-Bounded Online Ensemble Learning Framework With Mixed Feedback for Real-Time Safety Assessment

arXiv: https://arxiv.org/abs/2503.15581 · HTML: https://mlsanity.com/paper/2503.15581/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 47 references that are in the map.
- First posted on arXiv 19 Mar 2025.

## Builds on (most cited first, 8 of 8)

- [Learning under Concept Drift: A Review](https://mlsanity.com/paper/2004.05785/) (2020)
- [Class-Incremental Learning: A Survey](https://mlsanity.com/paper/2302.03648/) (2023)
- [Learning from Complementary Labels](https://mlsanity.com/paper/1705.07541/) (2017)
- [Active learning for data streams: a survey](https://mlsanity.com/paper/2302.08893/) (2023)
- [Online Ensemble Learning for Imbalanced Data Streams](https://mlsanity.com/paper/1310.8004/) (2013)
- [Dynamic Ensemble Active Learning: A Non-Stationary Bandit with Expert Advice](https://mlsanity.com/paper/1810.07778/) (2018)
- [Adaptive Ensemble Learning with Confidence Bounds](https://mlsanity.com/paper/1512.07446/) (2015)
- [Robust Sequential Online Prediction with Dynamic Ensemble of Multiple Models: A Review](https://mlsanity.com/paper/2112.02374/) (2021)

## Built on by (most cited first, 2 of 2)

- [VLSA: Vision-Language-Action Models with Plug-and-Play Safety Constraint Layer](https://mlsanity.com/paper/2512.11891/) (2025)
- [Lite-RVFL: A Lightweight Random Vector Functional-Link Neural Network for Learning Under Concept Drift](https://mlsanity.com/paper/2506.08063/) (2025)

## Abstract (arXiv)

Real-time safety assessment is critical for ensuring the reliable operation of complex dynamic systems. However, obtaining full safety labels in real time is often prohibitively expensive, resulting in a challenging mixed-feedback scenario dominated by partial feedback, especially under concept drift. Furthermore, existing online ensemble methods typically rely on heuristic weight allocation, lacking provable performance guarantees under such limited-feedback conditions. To address these challenges, we propose PB-OEL, a performance-bounded online ensemble learning framework designed for real-time safety assessment under mixed feedback. At the ensemble level, a theoretical framework is established to bound the performance of the ensemble classifier relative to its base classifiers across varying feedback ratios. By formally defining the form of expert advice, the bound guarantees that the ensemble outperforms any individual base classifier over a sufficiently large data stream. At the base-classifier level, a penalty-based update strategy is introduced, enabling base models to explicitly leverage misclassified samples rather than simply discarding them. Extensive experiments on the real-world Jiaolong manned submersible dataset demonstrate that PB-OEL maintains robust predictive performance and outperforms state-of-the-art methods.