Efficient Training on Very Large Corpora via Gramian Estimation
international conference on learning representations, 2019.
We study the problem of learning similarity functions over very large corpora using neural network embedding models. These models are typically trained using SGD with sampling of random observed and unobserved pairs, with a number of samples that grows quadratically with the corpus size, making it expensive to scale to very large corpora....More
PPT (Upload PPT)