Research

Embedding representations power machine intelligence in many applications, including recommendation systems, but they are space intensive — potentially occupying hundreds of gigabytes in large-scale settings. To help manage this outsized memory consumption, we explore mixed dimension embeddings, an embedding layer architecture in which a particular embedding vector’s dimension scales with its query frequency. Through theoretical analysis and systematic experiments, we demonstrate that using mixed dimensions can drastically reduce the memory usage, while maintaining and even improving the ML performance. Empirically, we show that the proposed mixed dimension layers improve accuracy by 0.1% using half as many parameters or maintain it using 16× fewer parameters for click-through rate prediction on the Criteo Kaggle dataset. They also train over 2× faster on a GPU.

A full version of this paper is accessible here.