Nvidia released the open beta of its deep learning recommender building framework Nvidia Merlin. A recommender system is a machine learning model which recommends users about the things to purchase or movies to watch based on previous data or based on choices of similar users. Recommender systems are the reason for meteorical rise of companies like Netflix and Amazon. They use either collaborative filtering or content based filtering or a combination of both. Building large scale recommenders is a challenge in itself.
Merlin empowers data scientists, machine learning engineers, and researchers to build high-performing recommenders at scale. Merlin includes tools that democratize building deep learning recommenders that provide better predictions than traditional methods and increase click-through rates. Each stage of the Merlin pipeline is optimized to support hundreds of terabytes of data, all accessible through easy-to-use APIs.
It has two parts
NVTabular reduces data preparation time by GPU-accelerating feature transformations and preprocessing.
HugeCTR is a deep neural network training framework that is capable of distributed training across multiple GPUs and nodes for maximum performance.
NVTabular is a feature engineering and preprocessing library designed to quickly and easily manipulate terabytes of recommender system datasets. It provides a high level abstraction and accelerates computation on GPUs using the RAPIDS cuDF library.
HugeCTR is a highly efficient C++ framework designed for distributed training with model-parallel embedding tables and data-parallel neural networks. HugeCTR covers common and recent architectures such as Deep Learning Recommendation Model (DLRM), Wide and Deep, Deep Cross Network, and DeepFM