Logit-Based Ensemble Distribution Distillation for Robust Autoregressive Sequence Uncertainties

Yassir Fathullah, Guoxuan Xia, Mark Gales

Keywords: uncertainty, autoregressive, ensemble distribution distillation, logit space, laplace distribution

TL;DR: Propose to distribution distill an autoregressive ensemble using a student Laplace distribution

Abstract: Efficiently and reliably estimating uncertainty is an important objective in deep learning. It is especially pertinent to autoregressive sequence tasks, where training and inference costs are typically very high. However, existing research has predominantly focused on tasks with static data such as image classification. In this work, we investigate Ensemble Distribution Distillation (EDD) applied to large-scale natural language sequence-to-sequence data. EDD aims to compress the superior uncertainty performance of an expensive (teacher) ensemble into a cheaper (student) single model. Importantly, the ability to separate knowledge (epistemic) and data (aleatoric) uncertainty is retained. Existing probability-space approaches to EDD, however, are difficult to scale to large vocabularies. We show, for modern transformer architectures on large-scale translation tasks, that modelling the ensemble \textit{logits}, instead of softmax probabilities, leads to significantly better students. Moreover, the students surprisingly even \textit{outperform Deep Ensembles} by up to $\sim$10\% AUROC on out-of-distribution detection, whilst matching them at in-distribution translation.