Variational Learning Induces Adaptive Label Smoothing

Sin-Han Yang, Zhedong Liu, Gian Maria Marconi, Mohammad Emtiyaz Khan

Abstract: We show that variational learning naturally induces an adaptive label smoothing where label noise is specialized for each example. Such label-smoothing is useful to handle examples with labeling errors and distribution shifts, but designing a good adaptivity strategy is not always easy. We propose to skip this step and simply use the natural adaptivity induced during the optimization of a variational objective. We show empirical results where a variational algorithm called IVON outperforms traditional label smoothing and yields adaptivity strategies similar to those of an existing approach.~By connecting Bayesian methods to label smoothing, our work provides a new way to handle overconfident predictions.

Primary Area: Probabilistic Methods->Variational Inference

Keywords: Label Smoothing, Variational Learning

Submission Number: 1474