- Abstract: In this paper we propose to perform model ensembling in a multiclass or a multilabel learning setting using Wasserstein barycenters. Optimal transport metrics, such as the Wasserstein distance, allow incorporating semantic side information such as word embeddings. Using Wass. barycenters to find the consensus between models allows us to balance confidence and semantics in finding the agreement between the models. We show applications of Wasserstein ensembling in attribute-based classification, multilabel learning and image captioning generation. These results show that the Wass. ensembling is a viable alternative to the basic geometric or arithmetic mean ensembling.
- Keywords: Wasserstein barycenter model ensembling
- TL;DR: we propose to use Wasserstein barycenters for semantic model ensembling