Tenrec: A Large-scale Multipurpose Benchmark Dataset for Recommender Systems
Authors:
- Guanghu YuanGYGuanghu Yuan
- Fajie YuanFYFajie Yuan
- Yudong LiYLYudong Li
- Beibei KongBKBeibei Kong
- Lei ChenLCLei Chen
- Min YangMin Yang
- Chenyun YuCYChenyun Yu
- Bo HuBHBo Hu
- Zang LiZLZang Li
- Yu XuYXYu Xu
- Xiaohu QieXQXiaohu Qie
Preprint
Abstract
Existing benchmark datasets for recommender systems (RS) either are created at a small scale or involve very limited forms of user feedback. RS models evaluated on such datasets often lack practical values for large-scale real-world applications. In this paper, we describe Tenrec, a novel and publicly available data collection for RS that records various user feedback from four different recommendation scenarios. To be specific, Tenrec has the following five characteristics: (1) it is large-scale, containing around 5 million users and 140 million interactions; (2) it has not only positive user feedback, but also true negative feedback (vs. one-class recommendation); (3) it contains overlapped users and items across four different scenarios; (4) it contains various types of user positive feedback, in forms of clicks, likes, shares, and follows, etc; (5) it contains additional features beyond the user IDs and item IDs. We verify Tenrec on ten diverse recommendation tasks by running several classical baseline models per task. Tenrec has the potential to become a useful benchmark dataset for a majority of popular recommendation tasks.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- Persia: An Open, Hybrid System Scaling Deep Learning-based Recommenders up to 100 Trillion Parameters2022
- Top-N Recommendation Algorithms: A Quest for the State-of-the-Art2022
- Contrastive Learning for Sequential Recommendation2022
- A Troubling Analysis of Reproducibility and Progress in Recommender Systems ResearchACM Transactions on Information Systems, 2021
- Empirical analysis of session-based recommendation algorithmsUser Modeling and User-Adapted Interaction, 2020
- A Generic Network Compression Framework for Sequential Recommender Systems2020
- Parameter-Efficient Transfer from Sequential Behaviors for User Modeling and Recommendation2020
- Future Data Helps Training: Modeling Future Contexts for Session-based Recommendation2020
- A Simple Convolutional Generative Network for Next Item Recommendation2019
- Matrix Factorization Techniques for Recommender SystemsComputer, 2009