Learning Prediction Intervals for Model Performance
This work aims to make automated model performance prediction more trustworthy and practical for AI system developers and maintainers by quantifying prediction uncertainty, which is an incremental improvement to existing techniques.
This paper addresses the challenge of predicting model performance on unlabeled data by developing a method to compute prediction intervals for model performance. Their approach uses transfer learning to train an uncertainty model, demonstrating substantial improvement over competitive baselines across various drift conditions.
Understanding model performance on unlabeled data is a fundamental challenge of developing, deploying, and maintaining AI systems. Model performance is typically evaluated using test sets or periodic manual quality assessments, both of which require laborious manual data labeling. Automated performance prediction techniques aim to mitigate this burden, but potential inaccuracy and a lack of trust in their predictions has prevented their widespread adoption. We address this core problem of performance prediction uncertainty with a method to compute prediction intervals for model performance. Our methodology uses transfer learning to train an uncertainty model to estimate the uncertainty of model performance predictions. We evaluate our approach across a wide range of drift conditions and show substantial improvement over competitive baselines. We believe this result makes prediction intervals, and performance prediction in general, significantly more practical for real-world use.