.png){kind=icon}
.png){kind=icon}
Return
AutoSR: Automatic Sequential Recommendation System Design
.png){kind=icon}
PRE
AI
DOI：10.1109/TKDE.2024.3400031.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Sequential Recommendation (SR) System emerged recently as a powerful tool for suggesting users with the next item of interest. Despite their great success, the design of SR systems requires heavy manual work and domain knowledge. In this paper, we present AutoSR, an effective Auto mated Machine Learning (AutoML) tool that enables automatic design of powerful SR systems based on Graph Neural Network (GNN) and Reinforcement Learning (RL). In AutoSR, we summarize the design process of the SR systems and extract effective operations from the existing SR systems to construct our search space. Such an experience-based search space generates diverse SR systems by integrating effective operations of different systems, providing a basic condition for the implementation of AutoML. Besides, we propose a graph-based RL method to efficiently explore the SR search space, where operations have complex and diverse application conditions. Compared with the existing AutoML methods, which ignore potential relations among operations, AutoSR can greatly avoid invalid SR system design and efficiently discover more powerful SR systems by analyzing the relation graph of various operations. Extensive experimental results show that AutoSR can gain powerful SR systems, superior to the existing AutoSR systems used for search space construction. Besides, AutoSR is more efficient than the existing AutoML algorithms in SR system design, which demonstrate the superiority of AutoSR.
Keywords:
Training
Machine learning
Search problems
Recommender systems
Space exploration
Graph neural networks
Task analysis
Automated machine learning
graph based reinforcement learning
sequential recommendation system
Journal
IF:
10.4
Papers:
6.8K
Citations:
3.2W