NVIDIA at RecSys 2021

Sept 27 - Oct 1, 2021

Join NVIDIA online at the 15th annual ACM Conference on Recommender Systems (RecSys 2021) 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.

 

Explore NVIDIA’s Transformers4Rec—an open-source library built on HuggingFace’s Transformers library that makes advances of NLP-based transformers to the recommender system community for sequential and session-based recommendation tasks. This paper demonstrates Transformers4Rec's usefulness and the applicability of transformer architectures in next-click prediction for user sessions, where sequence lengths are much shorter than those commonly found in NLP.

Conference Schedule at a Glance

At RecSys 2021, 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 and join us at either of our coffee breaks to be entered into a drawing to win a GeForce RTX™ 3090.

TUESDAY 28/09 WEDNESDAY 29/09 THURSDAY 30/09 FRIDAY 01/10 SATURDAY 02/10
End-to-End Session-Based Recommendation on GPU
(Tutorial)


9:30 - 1:00 p.m. CEST
Knowledge Graph Attention for Sequential Recommendations
(Research Paper)


3:00 - 7:00 p.m. CEST
Coffee Break
Join us to enter our GeForce RTX 3090 giveaway.

3:30 - 4:00 p.m. CEST
Transformers4Rec: Bridging the Gap between NLP and Sequential / Session-Based Recommendation
(Research Paper)


4:00 - 4:30 p.m. CEST
Coffee Break
Join us to enter our GeForce RTX 3090 giveaway.

5:30 - 6:00 p.m. CEST
GPU Accelerated Boosted Trees and Deep Neural Networks for Better Recommender Systems
(Research Paper)


6:00 - 6:30 p.m. CEST

Don’t miss a session. Register now for RecSys 2021.

Virtual Theater

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

 Virtual Theater - On-demand Talks at your place

Top Recommender System Resources

Transformers4Rec Research Paper

Transformers4Rec Research Paper

NVIDIA’s Transformers4Rec library helps machine learning engineers and data scientists explore and apply transformers architectures when building sequential and session-based recommendation pipelines. Register for our session at RecSys 2021 or download our paper to learn more.

RecSys Challenge Research Paper

RecSys Challenge Research Paper

In this paper, we present our first-place solution of the ACM RecSys 2021 challenge. Our final submission is an ensemble of stacked models using in total five XGBoost models and three neural networks. Register for our session at RecSys 2021 or download our paper to learn more.

HugeCTR TensorFlow Plugin Technical Blog

HugeCTR TensorFlow Plugin Technical Blog

NVIDIA Merlin™ optimized embedding implementation is up to 8x more performant than other frameworks’ embedding layers and is available as a TensorFlow (TF) Plugin. It works seamlessly with TF and as a drop-in replacement for native TF embedding layers.

Sequential and Session-Based Recommendation Blog

Sequential and Session-Based Recommendation Blog

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.

NVIDIA Merin

NVIDIA Merlin

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.

 NVIDIA Wins RecSys Challenges

NVIDIA Wins RecSys Challenges

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

Neural Networks for Your Recommender System

Neural Networks for Recommenders

Deep learning methods provide better prediction at scale for building recommenders. Learn how these methods used by our award-winning recommender system team could be the key to optimizing your recommender system.

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

Congratulations to our Contest Winners!

This year, the NVIDIA KGMON, Merlin, and RAPIDS.AI team earned first place in the ACM RecSys2021 Challenge, SIGIR eCom Data Challenge, and Booking.com Challenge. Congratulations to all of our participants!

Booking.com Challenge

Benedikt Schifferer
Chris Deotte
Jean-Francois Puget
Gabriel de Souza Pereira Moreira
Gilberto Titericz
Jiwei Liu
Ronay Ak 

ACM RecSys Challenge

Chris Deotte
Bo Liu
Benedikt Schifferer
Gilberto Titericz
Ronay Ak
Jiwei Liu
Gabriel De Souza Pereira Moreira

SIGIR eCom Data Challenge

Ronay Ak
Sara Rabhi 
Md Yasin Kabir
Gabriel Moreira

NVIDIA Developer Program

Get the advanced tools and training you need to successfully build applications on all NVIDIA technology platforms.

NVIDIA Developer Program

NVIDIA Deep Learning Institute (DLI)

Get Hands-On Training in AI, HPC, Accelerated Data Science, and more

Develop the skills you need to do your life’s work through the NVIDIA Deep Learning Institute (DLI). Choose from an extensive catalog of hands-on, instructor-led workshops or self-paced online training, and benefit from access to GPUs in the cloud. You can also take select courses that provide a certificate of competency to support your professional career growth.

Popular Self-Paced Courses

Getting Started with Deep Learning
Accelerating End-to-End Data Science Workflows

Instructor-led Workshops:

Building Transformer-Based Natural Language Processing Applications
Join at GTC on November 8th. Register now

Building Intelligent Recommender Systems
Public workshop on November 23rd
Register now and use code DLIRECSYS21 to receive 25% discount

Building Conversational AI Applications
Public workshop on November 24th 
Register now and use code DLIRECSYS21 to receive 25% discount

Sign up to receive the latest news from NVIDIA