profile-pic
LargeRecSys
The workshop for large scale recommender systems, held in conjunction with VideoRecSys at the 2024 ACM conference on Recommender Systems.

Introduction


Recommender systems are ubiquitous across many domains such as entertainment, e-commerce, news, social media, fitness, e-commerce and education, and as such, the need to think about the problems at scale is ever growing. As the Scaling Law in Recommender Systems becomes more apparent, the demand for billion-parameter or even trillion-parameter models in Recommender Systems is increasing to unprecedented levels. When implemented within industry settings, these systems encounter many real-world constraints and complexities that require tailored solutions. Designing and maintaining recommender systems that operate at a massive scale come with their own set of distinct algorithmic, systematic, and ethical challenges.

LargeRecSys workshop aims to bridge the gap between state-of-the-art RecSys research and the practical demands of operating large recommender systems at scale. We plan to invite researchers and practitioners from both industry and academia to engage in discussions and challenges inherent in large-scale recommender systems.

Keynote and Invited Speakers


Lexi Baugher

Lexi Baugher

Lexi Baugher is a Distinguished Software Engineer at YouTube. She got her Bachelor of Science from Caltech in Engineering and Applied Science. She has worked at Google for 23 years. She is currently the Area Tech Lead of YouTube Discovery, overseeing development of YouTube's recommendation systems. She lives in San Francisco with her husband, kid, and cat; and enjoys baseball, running and baking.

Justin Basilico

Justin Basilico

Justin Basilico is a research/engineering director at Netflix. He leads the recommendations algorithms team that does research and development of the machine learning algorithms used to power the core Netflix experience and personalize it for our members worldwide. Prior to Netflix, he worked in the Cognitive Systems group at Sandia National Laboratories. He has an MS in Computer Science from Brown University and a BA in Computer Science from Pomona College.

Chris Johnson

Chris Johnson

Chris Johnson is a Senior Director of Data Science at Indeed where he leads the Match Recommendations organization, powering match recommendations for both Jobseekers and Employers across Indeed surfaces. Chris previously led the Homepage Personalization team at Amazon and the Recommendations team at Spotify and brings over a decade of experience building large scale recommender systems. He completed his Masters degree in Computer Science at The University of Texas at Austin and his research has been featured at top ML conferences including NeuRIPS, AISTATS, and RecSys.

Xinghai Hu

Xinghai Hu

Xinghai Hu is the lead of the responsible recommendation system team at TikTok. His work involves building machine learning solutions for user growth, content ecosystem health and diversification, and algorithm trust and responsibility. Before joining TikTok, he worked at Facebook and Netflix. He holds an MS degree from Carnegie Mellon University.

Jiajing Xu

Jiajing Xu

Jiajing Xu is a senior ML engineering director at Pinterest. He heads the Applied Science team, which brings cutting-edge solutions to the company’s most pressing challenges. The team tackles challenges in the areas of representation learning, recommendation system, generative AI, graph neural network, and inclusive AI. Prior to his current role, he co-founded the visual discovery team and managed the Ads Ranking team at Pinterest. He holds a Ph.D. and an M.S. from Stanford, and a Bachelor’s degree from Caltech, all in electrical engineering.

Schedule


Time Topic Speaker
9:00 - 9:05 Opening Remarks  
9:05 - 9:35 Keynote: Putting the "You" in YouTube: Better Personalization through Larger Models Lexi Baugher, YouTube
9:35 - 10:00 Invited Talk: Creating Reliable Recommender Systems Xinghai Hu, TikTok
10:00 - 10:20 Invited Talk: TorchRec Dennis van der Staay, Meta
10:20 - 10:30 Spotlight Talk: WebReco: A Comprehensive Overview of an Industrial Scale Webpage RecSys at Bing Jaidev Shah, Microsoft
10:30 - 11:00 Coffee Break  
11:00-11:30 Keynote: Raising a (teenage) Recommender System: 13 lessons learned Justin Basilico, Netflix
11:30-11:55 Invited Talk: Inspiring Discovery - Recent Advances in Pinterest's Recommender System Jiajing Xu, Pinterest
11:55-12:20 Invited Talk: Phases of Recommender Systems Chris Johnson, Indeed
12:20-12:30 Spotlight Talk: Transformers for Large Scale Sequential Recommendations Aleksandr V. Petrov, University of Glasgow

Accepted Contributions


  • [Spotlight] Transformers for Large Scale Sequential Recommendation
    Aleksandr Vladimirovich Petrov, Craig Macdonald and Nicola Tonellotto
  • [Spotlight] WebReco: A Comprehensive Overview of an Industrial-Scale Webpage Recommendation System at Bing
    Jaidev Shah, Amey Barapatre, Iman Barjasteh, Chuck Wang, Gang Luo, Rana Forsati, Jing Chu, Xugang Wang, Julie Fang, Fan Wu, Jiahui Liu, Xue Deng, Blake Shepard, Ronak Shah, Shaden Smith, Jonathan Soifer, Linjun Yang, Chuanjie Liu and Hongzhi Li
  • Item Level Exploration Traffic Allocation in Large-scale Recommendation System
    Dong Wang, Arnab Bhadury, Junyi Jiao, Yaping Zhang and Mingyan Gao
  • CADC: Encoding User-Item Interactions for Compressing Recommendation Model Training Data
    Hossein Entezari Zarch, Abdulla Alshabanah, Chaoyi Jiang and Murali Annavaram
  • ERCache: An Efficient and Reliable Caching Framework for Large-Scale User Representations in Meta's Ads System
    Fang Zhou, Yaning Huang, Dong Liang, Dai Li, Zhongke Zhang, Kai Wang, Xiao Xin, Abdallah Aboelela, Zheliang Jiang, Yang Wang, Jeff Song, Wei Zhang, Chen Liang, Huayu Li, Hang Yang, Lei Qu, Zhan Shu, Mindi Yuan, Emanuele Maccherani, Taha Haya, John Guo, Varna Puvvada, Uladzimir Pashkevich and Chonglin Sun
  • Evaluating Performance and Bias of Negative Sampling in Large-Scale Sequential Recommendation Models
    Arushi Prakash, Dimitrios Bermperidis and Srivas Chennu
  • Data Leakage in Recommendation System A/B Tests
    Roshni Sahoo, Jennifer Brennan, Zak Mhammedi and Jean Pouget-Abadie

Organizers