Wasserstein Barycenter Model Ensembling

Understand

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.