Search Results for author:
Found 2 papers, 0 papers with code
Saec: Similarity-Aware Embedding Compression in Recommendation Systems
Production recommendation systems rely on embedding methods to represent various features.
Stanza: Layer Separation for Distributed Training in Deep Learning
Thus, we propose layer separation in distributed training: the majority of the nodes just train the convolutional layers, and the rest train the fully connected layers only.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
