Ensembling

# Entropy Minimized Ensemble of Adapters

Introduced by Wang et al. in Efficient Test Time Adapter Ensembling for Low-resource Language Varieties

Entropy Minimized Ensemble of Adapters, or EMEA, is a method that optimizes the ensemble weights of the pretrained language adapters for each test sentence by minimizing the entropy of its predictions. The intuition behind the method is that a good adapter weight $\alpha$ for a test input $x$ should make the model more confident in its prediction for $x$, that is, it should lead to lower model entropy over the input

#### Papers

Paper Code Results Date Stars