Harnessing Explainability to Improve ML Ensemble Resilience
Bibliographic record
Abstract
Safety-critical applications such as healthcare and autonomous vehicles, utilize machine learning (ML), where mispredictions could have disastrous consequences. Training data can contain faults, especially when collected through crowdsourcing. Ensembles, consisting of multiple ML models voting on predictions, have been found to be an effective resilience technique. Ensembles are resilient when their constituent models behave independently during inference, by focusing on different features in an input. However, independence is not observed on every input, resulting in mispredictions. One way to improve ensemble resilience is to dynamically weigh predictions during inference by its constituent models instead of treating each model equally. While previous work on dynamically weighted models in ensembles has relied upon output diversity metrics due to efficiency, we focus on the feature-space of inputs for accuracy. Hence, we propose the use of explainable artificial intelligence (XAI) techniques to dynamically adjust the weight of ensemble models based on local feature-space diversity.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".