NVIDIA at RecSys 2022

Sept 18–23, 2022

Join NVIDIA at the 16th annual ACM Conference on Recommender Systems (RecSys 2022) to see how new research results, methods, libraries, and techniques in the broad field of recommender systems are driving our future. We’ll feature our own virtual theater with speakers from a variety of leading industries and domains, along with demos, related content, and more.

Conference Schedule at a Glance

At RecSys 2022, you can explore a range of groundbreaking work in the field of recommender systems. Take a closer look at the scheduled NVIDIA sessions that are part of this year’s program.

Don’t miss a session. Register now for RecSys 2022.

Virtual Theater

Hear from industry leaders, data scientists, and engineers as they explain their groundbreaking work for building, training, optimizing, and deploying recommender systems.

 Virtual Theater - On-demand Talks at your place

Top Recommender System Resources



Learn about NVIDIA Merlin, an open source framework for building recommender systems. Merlin empowers data scientists, machine learning engineers, and researchers to build high-performing recommenders at scale.

Hierarchical Parameter Server

Hierarchical Parameter Server (HPS)

In this ACM RecSys 2022 accepted paper, discover how HPS combines a high performance GPU embeddings cache with an hierarchical storage architecture to realize low-latency retrieval of embeddings for online model inference.

Four stages of recommender systems

Recommender Systems, Not Just Recommender Models

Read about a four-stage design pattern that builds understanding and consensus about what recommender systems (not just models) look like in production.

Multi-Stage Recommender Systems Tutorial

Multi-Stage Recommender Systems Tutorial

Attend this hands-on ACM RecSys 2022 Tutorial and dive into how to make developing and deploying recommender systems easier. Covers methods for evaluating existing approaches, developing new ideas, and deploying them to production.

GPU Accelerated Recommender Systems Training and Inference

GPU Accelerated Recommender Systems Training and Inference

In this ACM RecSys 2022 accepted submission, learn about NVIDIA Merlin HugeCTR, a framework for click through rate estimation that is optimized for training and inference. It also enables training at scale with model-parallel embeddings and data-parallel neural networks.

Reduce model development friction with Merlin Models

Reduce Model Development Friction

With the Merlin Models library, access common architectures that can be coupled with different prediction tasks, loss functions, and negative sampling strategies to ease development and deployment.

Exploring Product Ready Recommenders with Merlin

Exploring Production Ready Recommenders

Deploying custom models to production is a challenge. Explore potential ways to ease deployment with Merlin Systems in this blog post.

2nd Annual Recommender Systems Summit 2022

NVIDIA Recommender Summit 2022

During this NVIDIA AI online event, join fellow data scientists and engineers from Netflix, Twitter, NVIDIA, and more to discuss learnings and best practices on building and deploying effective recommender systems.

Two Tower architecture

Scale Faster with Two Tower and Merlin

Introduction to popular Two Tower architecture, why it solves for challenges associated with candidate retrieval, and how using Merlin Models enables training with 4 lines of code.

Sequential and Session-Based Recommendation

Sequential and Session-Based Recommendation

In this blog, we cover sequential and session-based recommendation tasks, including why it’s important and practical use cases. We also provide a brief overview of our Transformers4Rec solution.

Multi-Stage Recommender Systems Demo

Multi-Stage Recommender Systems Demo

In this ACM RecSys 2022 accepted submission, watch a technical walk through implementation of the four stages of recommender systems.



Watch NVIDIA CEO Jensen Huang discuss the importance of AI frameworks, including NVIDIA Merlin™, in the NVIDIA GTC keynote.

Large Scale Recommender System Inference

Large-scale Recommender System Inference

Serving user requests with low latency and high accuracy is critical for recommender systems. NVIDIA Merlin introduces HPS, a scalable solution with multilevel adaptive storage to enable deployment of Terabyte-size models under real-time latency constraints!

Training Terabyte-scale Recommender with Ease

Training Terabyte-scale Recommenders with Ease

In this post, learn how NVIDIA Merlin Distributed Embeddings enables developers to rapidly train Terabyte-scale embedding based models in TensorFlow 2 with just a few lines of code! 

 NVIDIA Wins RecSys Challenges

NVIDIA Wins RecSys Challenges

Industry challenges help advance the recommender system field for everyone. NVIDIA’s wins are fueling ideas for new techniques into recsys frameworks like NVIDIA Merlin.

Recommender Systems Best Practices

Recommender Systems Best Practices

Read about the latest trends for recommender system practices within industry. The whitepaper includes insights from industry leads from companies such as Tencent, Meituan, Wayfair, Magazine Luiza, The New York Times, and more.

The Developer Conference
for the Era of AI and the

Join us this September for a GTC that will inspire your next big idea. This is a don't miss opportunity to learn from experts and leaders in their fields on how AI is transforming industries and profoundly impacting the world. It all happens online SeptemberSep 19-22.

NVIDIA Developer Program

Join the NVIDIA Developer Program and receive exclusive access to tools, SDKs, webinars, early access programs, community forums, NVIDIA On-Demand (NVIDIA’s repository of over 7,000 technical sessions), and more.

NVIDIA Deep Learning Institute (DLI)

Get Technical Training at GTC, September 19-22, 2022

The NVIDIA Deep Learning Institute (DLI) is offering a variety of hands-on full-day workshops and training labs covering AI, accelerated computing, and data science at GTC, September 19-22, 2022.

During the workshops, you’ll get access to a fully configured, GPU-accelerated server in the cloud, gain practical skills for your work, and even earn a certificate of subject matter competency. The 2-hour training labs are included in the free GTC conference pass.

Popular Training Labs

Training and Deploying Multi-Stage Recommender Systems

Accelerating and Scaling Inference with NVIDIA GPUs

Introduction to Graph Neutral Networks

View All Training Labs

Sign up to receive the latest news from NVIDIA