Generalization is not a universal guarantee: Estimating similarity to training data with an ensemble out-of-distribution metric
This addresses the reliability of AI systems by providing a standardized approach for data comparison, though it is incremental as it builds on existing out-of-distribution detection methods.
The paper tackles the problem of machine learning models failing to generalize to new data by proposing SAGE, a model-agnostic method for assessing data similarity, which improves out-of-the-box model performance on datasets like MNIST, CIFAR-10, and UCI Abalone after filtering.
Failure of machine learning models to generalize to new data is a core problem limiting the reliability of AI systems, partly due to the lack of simple and robust methods for comparing new data to the original training dataset. We propose a standardized approach for assessing data similarity in a model-agnostic manner by constructing a supervised autoencoder for generalizability estimation (SAGE). We compare points in a low-dimensional embedded latent space, defining empirical probability measures for k-Nearest Neighbors (kNN) distance, reconstruction of inputs and task-based performance. As proof of concept for classification tasks, we use MNIST and CIFAR-10 to demonstrate how an ensemble output probability score can separate deformed images from a mixture of typical test examples, and how this SAGE score is robust to transformations of increasing severity. As further proof of concept, we extend this approach to a regression task using non-imaging data (UCI Abalone). In all cases, we show that out-of-the-box model performance increases after SAGE score filtering, even when applied to data from the model's own training and test datasets. Our out-of-distribution scoring method can be introduced during several steps of model construction and assessment, leading to future improvements in responsible deep learning implementation.