Large Scale Recommender System

Large-scale recommender systems aim to provide personalized recommendations efficiently to vast user bases, focusing on maximizing user engagement and other key performance indicators (KPIs). Current research emphasizes improving efficiency and accuracy through techniques like reinforcement learning (for optimizing resource allocation and multi-task fusion), novel model architectures such as Mamba (to reduce computational complexity), and advanced methods to address challenges like embedding collapse and conformity bias. These advancements are crucial for enhancing the performance and scalability of recommender systems across various applications, impacting fields from e-commerce and advertising to media streaming and social platforms.

Papers

November 15, 2024

KuaiFormer: Transformer-Based Retrieval at Kuaishou
Chi Liu, Jiangxia Cao, Rui Huang, Kai Zheng, Qiang Luo, Kun Gai, Guorui Zhou
App to App Retrieval Large Scale Recommender System Retrieval Enhanced Transformer Large Scale Recommendation Large Scale Recommendation System

October 15, 2024

October 8, 2024

Data Efficiency for Large Recommendation Models
Kshitij Jain, Jingru Xie, Kevin Regan, Cheng Chen, Jie Han, Steve Li, Zhuoshu Li, Todd Phillips, Myles Sussman, Matt Troup, Angel Yu, Jia Zhuo
CTR Prediction Data Efficiency Large Scale Recommender System Network Convergence

September 23, 2024

Combining Open-box Simulation and Importance Sampling for Tuning Large-Scale Recommenders
Kaushal Paneri, Michael Munje, Kailash Singh Maurya, Adith Swaminathan, Yifan Shi
Recommender System Open Source Importance Sampling Monte Carlo Hyper Tune Large Scale Recommender System Ad Placement

September 20, 2024

RPAF: A Reinforcement Prediction-Allocation Framework for Cache Allocation in Large-Scale Recommender Systems
Shuo Su, Xiaoshuang Chen, Yao Wang, Yulin Wu, Ziqiang Zhang, Kaiqiao Zhan, Ben Wang, Kun Gai
Reinforcement Learning Modern Recommender System Cache Context Caching Strategy Large Scale Recommender System rEward Decomposition Adaptive Streaming

September 18, 2024

An Enhanced-State Reinforcement Learning Algorithm for Multi-Task Fusion in Large-Scale Recommender Systems
Peng Liu, Jiawei Zhu, Cong Xu, Ming Zhao, Bin Wang
Reinforcement Learning Recommender System Multi Task Learning Recommendation Quality Large Scale Recommender System Multi Task Fusion

September 11, 2024

Mamba for Scalable and Efficient Personalized Recommendations
Andrew Starnes, Clayton Webster
Potential Scalability Recommendation System Mamba in Mamba Large Scale Recommender System Efficient Recommender System Different Recommendation

May 21, 2024

Enhancing User Interest based on Stream Clustering and Memory Networks in Large-Scale Recommender Systems
Peng Liu, Nian Wang, Cong Xu, Ming Zhao, Bin Wang, Yi Ren
Recommender System User Interest Memory Network Large Scale Recommender System Sparse Text

April 23, 2024

Cache-Aware Reinforcement Learning in Large-Scale Recommender Systems
Xiaoshuang Chen, Gengrui Zhang, Yao Wang, Yulin Wu, Shuo Su, Kaiqiao Zhan, Ben Wang
Reinforcement Learning Recommender System User Behavior Cache Context Large Scale Recommender System

April 19, 2024

An Off-Policy Reinforcement Learning Algorithm Customized for Multi-Task Fusion in Large-Scale Recommender Systems
Peng Liu, Cong Xu, Ming Zhao, Jiawei Zhu, Bin Wang, Yi Ren
Reinforcement Learning Multi Task Learning Policy Reinforcement Learning Efficient Exploration Exploration Policy Large Scale Recommender System Multi Task Fusion

January 9, 2024

G-Meta: Distributed Meta Learning in GPU Clusters for Large-Scale Recommender Systems
Youshao Xiao, Shangchun Zhao, Zhenglei Zhou, Zhaoxin Huan, Lin Ju, Xiaolu Zhang, Lin Wang, Jun Zhou
GPU Cluster Deep Learning Pipeline Large Scale Training Large Scale Recommender System Deep Learning Recommendation Model Optimization Based Meta Learning

October 6, 2023

On the Embedding Collapse when Scaling up Recommendation Models
Xingzhuo Guo, Junwei Pan, Ximei Wang, Baixu Chen, Jie Jiang, Mingsheng Long
Recommendation Model Event Collapse Multiple Embeddings Large Scale Recommender System Scalable Model

July 25, 2023

Unleash the Power of Context: Enhancing Large-Scale Recommender Systems with Context-Based Prediction Models
Jan Hartman, Assaf Klein, Davorin Kopič, Natalia Silberstein
Context Information Real Power Context Aware Personalized Recommendation CTR Prediction Large Scale Recommender System

April 17, 2023

CAM2: Conformity-Aware Multi-Task Ranking Model for Large-Scale Recommender Systems
Ameya Raul, Amey Porobo Dharwadker, Brad Schumitsch
Large Scale Industrial Recommender System Large Scale Recommender System Conformity Bias

April 13, 2023

PIE: Personalized Interest Exploration for Large-Scale Recommender Systems
Khushhall Chandra Mahajan, Amey Porobo Dharwadker, Romil Shah, Simeng Qu, Gaurav Bang, Brad Schumitsch
Recommender System Large Scale User Interest Large Scale Recommender System

December 20, 2022

Variational Factorization Machines for Preference Elicitation in Large-Scale Recommender Systems
Jill-Jênn Vie, Tomas Rigaux, Hisashi Kashima
Matrix Factorization Collaborative Filtering Preference Elicitation Mini Batch Gradient Descent Factorization Machine Large Scale Recommender System Bayesian Formulation

July 21, 2022

The trade-offs of model size in large recommendation models : A 10000 $\times$ compressed criteo-tb DLRM model (100 GB parameters to mere 10MB)
Aditya Desai, Anshumali Shrivastava
Model Size Machine Learning Benchmark Large Scale Recommender System Deep Learning Recommendation Model Memory Deep Learning Deep Recommendation

May 18, 2022

Efficient Mixed Dimension Embeddings for Matrix Factorization
Dmitrii Beloborodov, Andrei Zimovnov, Petr Molodyk, Dmitrii Kirillov
Recommender System Matrix Factorization Dimensional Embeddings Large Scale Recommender System

February 7, 2022

Bayesian Non-stationary Linear Bandits for Large-Scale Recommender Systems
Saeed Ghoorchian, Evgenii Kortukov, Setareh Maghsudi
Recommender System Linear Bandit Non Stationary Linear Contextual Bandit Large Scale Recommender System Policy Sampling

Large Scale Recommender System

Papers

KuaiFormer: Transformer-Based Retrieval at Kuaishou

Understanding and Scaling Collaborative Filtering Optimization from the Perspective of Matrix Rank

Fast Second-Order Online Kernel Learning through Incremental Matrix Sketching and Decomposition

Data Efficiency for Large Recommendation Models

Combining Open-box Simulation and Importance Sampling for Tuning Large-Scale Recommenders

RPAF: A Reinforcement Prediction-Allocation Framework for Cache Allocation in Large-Scale Recommender Systems

An Enhanced-State Reinforcement Learning Algorithm for Multi-Task Fusion in Large-Scale Recommender Systems

Mamba for Scalable and Efficient Personalized Recommendations

Enhancing User Interest based on Stream Clustering and Memory Networks in Large-Scale Recommender Systems

Cache-Aware Reinforcement Learning in Large-Scale Recommender Systems

An Off-Policy Reinforcement Learning Algorithm Customized for Multi-Task Fusion in Large-Scale Recommender Systems

G-Meta: Distributed Meta Learning in GPU Clusters for Large-Scale Recommender Systems

On the Embedding Collapse when Scaling up Recommendation Models

Unleash the Power of Context: Enhancing Large-Scale Recommender Systems with Context-Based Prediction Models

CAM2: Conformity-Aware Multi-Task Ranking Model for Large-Scale Recommender Systems

PIE: Personalized Interest Exploration for Large-Scale Recommender Systems

Variational Factorization Machines for Preference Elicitation in Large-Scale Recommender Systems

The trade-offs of model size in large recommendation models : A 10000 $\times$ compressed criteo-tb DLRM model (100 GB parameters to mere 10MB)

Efficient Mixed Dimension Embeddings for Matrix Factorization

Bayesian Non-stationary Linear Bandits for Large-Scale Recommender Systems