Using DLRM | Building Recommender Systems with PyTorch | Maxim Naumov and Dheevatsa Mudigere

In this tutorial series we show how to build deep learning recommendation systems and resolve the associated interpretability, integrity and privacy challenges. We start with an overview of the PyTorch framework, features that it offers and a brief review of the evolution of recommendation models. We delineate their typical components and build a proxy deep learning recommendation model (DLRM) in PyTorch. Then, we discuss how to interpret recommendation system results as well as how to address the corresponding integrity and quality challenges. The material for this section covers:

1. What is PyTorch? Joe Spisak/Geeta Chauhan

𝟮. 𝗥𝗲𝗰𝗼𝗺𝗺𝗲𝗻𝗱𝗲𝗿 𝗦𝘆𝘀𝘁𝗲𝗺𝘀 𝘂𝘀𝗶𝗻𝗴 𝗗𝗟𝗥𝗠 – 𝗠𝗮𝘅𝗶𝗺 𝗡𝗮𝘂𝗺𝗼𝘃/𝗗𝗵𝗲𝗲𝘃𝗮𝘁𝘀𝗮 𝗠𝘂𝗱𝗶𝗴𝗲𝗿𝗲

3. Using Captum for Interpretability for recommender systems – Narine Kokhlikyan
4. Solving integrity / QC challenges for recommender systems – Amanpreet Singh

Important references that will be covered in the tutorial:
Compositional Embeddings Using Complementary Partitions for Memory-Efficient Recommendation Systems (
Mixed Dimension Embeddings with Application to Memory-Efficient Recommendation Systems (
Deep Learning Inference in Facebook Data Centers: Characterization, Performance Optimizations and Hardware Implications (
Deep Learning Training in Facebook Data Centers: Design of Scale-up and Scale-out Systems (

Source of this PyTorch AI Video

AI video(s) you might be interested in …