Poster
Efficient Training on Very Large Corpora via Gramian Estimation
Walid Krichene · Nicolas Mayoraz · Steffen Rendle · Li Zhang · Xinyang Yi · Lichan Hong · Ed H. Chi · John Anderson
Great Hall BC #16
Keywords: [ variance reduction ] [ matrix factorization ] [ similarity learning ] [ pairwise learning ] [ gramian estimation ] [ neural embedding models ] [ recommender systems ]
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 random sampling of unobserved pairs, with a sample size that grows quadratically with the corpus size, making it expensive to scale. We propose new efficient methods to train these models without having to sample unobserved pairs. Inspired by matrix factorization, our approach relies on adding a global quadratic penalty and expressing this term as the inner-product of two generalized Gramians. We show that the gradient of this term can be efficiently computed by maintaining estimates of the Gramians, and develop variance reduction schemes to improve the quality of the estimates. We conduct large-scale experiments that show a significant improvement both in training time and generalization performance compared to sampling methods.
Live content is unavailable. Log in and register to view live content