Selective Ensembles for Consistent Predictions
Recent work has shown that models trained to the same objective, and which achieve similar measures of accuracy on consistent test data, may nonetheless behave very differently on individual predictions. This inconsistency is undesirable in high-stakes contexts, such as medical diagnosis and finance. We show that this inconsistent behavior extends beyond predictions to feature attributions, which may likewise have negative implications for the intelligibility of a model, and one's ability to find recourse for subjects. We then introduce selective ensembles to mitigate such inconsistencies by applying hypothesis testing to the predictions of a set of models trained using randomly-selected starting conditions; importantly, selective ensembles can abstain in cases where a consistent outcome cannot be achieved up to a specified confidence level. We prove that that prediction disagreement between selective ensembles is bounded, and empirically demonstrate that selective ensembles achieve consistent predictions and feature attributions while maintaining low abstention rates. On several benchmark datasets, selective ensembles reach zero inconsistently predicted points, with abstention rates as low 1.5%.
Code (0)
등록된 구현이 없습니다.
Tasks
Medical DiagnosisSimilar Papers 제목 키워드 기반
LSCP: Locally Selective Combination in Parallel Outlier Ensembles
In unsupervised outlier ensembles, the absence of ground truth makes the combination of base outlier detectors a challenging task. Specifically, existing parallel outlier ensembles lack a reliable way of selecting compet…
Anomaly DetectionOutlier Detectionoutlier ensemblesFedBiCross: Personalized One-Shot Federated Learning on Medical Images
Data-free knowledge distillation-based one-shot federated learning (OSFL) trains a model in a single communication round without sharing raw data, making OSFL attractive for privacy-sensitive medical applications. Howeve…
Data-free Knowledge DistillationFederated LearningASPEST: Bridging the Gap Between Active Learning and Selective Prediction
Selective prediction aims to learn a reliable model that abstains from making predictions when uncertain. These predictions can then be deferred to humans for further evaluation. As an everlasting challenge for machine l…
Active LearningPredictionTowards Consistent Predictive Confidence through Fitted Ensembles
Deep neural networks are behind many of the recent successes in machine learning applications. However, these models can produce overconfident decisions while encountering out-of-distribution (OOD) examples or making a w…
Out of Distribution (OOD) DetectionBeyond Modality Fusion: Deep Ensembles for Multimodal Classification
In multimodal classification, late-fusion approaches classify concatenated modality-specific features extracted by unimodal neural networks. When modality imbalance is pronounced, various regularization techniques have b…