Likelihood Ratios for Out-of-Distribution Detection
This addresses the critical need for safe deployment of classifiers in real-world applications like disease detection from genomic sequences, though it is incremental as it builds on existing deep generative model approaches.
The paper tackled the problem of out-of-distribution (OOD) detection in neural networks, where existing methods fail to provide reliable confidence estimates on unseen data, by proposing a likelihood ratio method that corrects for background statistics in deep generative models, achieving state-of-the-art performance on a genomics dataset and significantly improving OOD detection in image models.
Discriminative neural networks offer little or no performance guarantees when deployed on data not generated by the same process as the training distribution. On such out-of-distribution (OOD) inputs, the prediction may not only be erroneous, but confidently so, limiting the safe deployment of classifiers in real-world applications. One such challenging application is bacteria identification based on genomic sequences, which holds the promise of early detection of diseases, but requires a model that can output low confidence predictions on OOD genomic sequences from new bacteria that were not present in the training data. We introduce a genomics dataset for OOD detection that allows other researchers to benchmark progress on this important problem. We investigate deep generative model based approaches for OOD detection and observe that the likelihood score is heavily affected by population level background statistics. We propose a likelihood ratio method for deep generative models which effectively corrects for these confounding background statistics. We benchmark the OOD detection performance of the proposed method against existing approaches on the genomics dataset and show that our method achieves state-of-the-art performance. We demonstrate the generality of the proposed method by showing that it significantly improves OOD detection when applied to deep generative models of images.