papers AI Learner
The Github is limit! Click to go to the new site.

Wasserstein Barycenter Model Ensembling

2019-02-13
Pierre Dognin, Igor Melnyk, Youssef Mroueh, Jerret Ross, Cicero Dos Santos, Tom Sercu

Abstract

In this paper we propose to perform model ensembling in a multiclass or a multilabel learning setting using Wasserstein (W.) barycenters. Optimal transport metrics, such as the Wasserstein distance, allow incorporating semantic side information such as word embeddings. Using W. 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 W. ensembling is a viable alternative to the basic geometric or arithmetic mean ensembling.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1902.04999

PDF

https://arxiv.org/pdf/1902.04999


Similar Posts

Comments