NVIDIA Team wins the ACM RecSys Challenge 2020

It seems that NVIDIA becomes a new big player in the recommender-system community. After introducing Merlin – a Framework for Deep Recommender Systems – and offering an online course for Building Intelligent Recommender Systems, a team of NVIDIA employees now won the ACM RecSys Challenge 2020. The goal of the challenge was to “predict the probability for different types of engagement (Like, Reply, Retweet and Retweet with comment) of a target user for a set of tweets, based on heterogeneous input data”.

The original NVIDIA blog post announcing the success is rather a marketing story, but another post published by the team — Benedikt Schifferer, Gilberto Titericz Junior, Chris Deotte, Christof Henkel, Kazuki Onodera, Jiwei Liu, Bojan Tunguz, Even Oldridge, Gabriel De Souza Pereira Moreira, and Ahmet Erdem — on Medium is an interesting read. They explain how their GPU-based solution (4 x V100) is around 25 times faster than an Intel Xeon CPU (20 Cores). The team sees the high speed of their pipeline as a key contributor to their success.

Our approach achieved the highest score in seven of the eight metrics used to calculate the final leaderboard position. The acceleration of our pipeline was critical in our ability to quickly perform exploratory data analysis (EDA) and led to discovering a range of effective features used in the final solution […] Our GPU-optimized pipeline enabled us to quickly iterate on new ideas and run many experiments in a short time, giving us a competitive advantage to win this year’s competition.

https://miro.medium.com/max/3281/1*LeZeTRlKJWeDgTRzcDiO2A.jpeg

https://medium.com/rapids-ai/winning-solution-of-recsys2020-challenge-gpu-accelerated-feature-engineering-and-training-for-cd67c5a87b1f

Add a Comment

Your email address will not be published. Required fields are marked *