Pre-training graph transformer with multimodal side information for recommendation

Pre-training graph transformer with multimodal side information for recommendation

Side information of items, e.g., images and text description, has shown to be effective in contributing to accurate recommendations. Inspired by the recent success of pre-training models on natural language and images, we propose a pre-training strategy to learn item representations by considering b...

Full description

Bibliographic Details
Main Authors: Liu, Yong, Yang, Susen, Lei, Chenyi, Wang, Guoxin, Tang, Haihong, Zhang, Juyong, Sun, Aixin, Miao, Chunyan
Other Authors: School of Computer Science and Engineering
Format: Conference Paper
Language:English
Published: 2022
Subjects:
Engineering::Computer science and engineering
Recommendation Systems
Pre-Training Mode
Online Access:https://hdl.handle.net/10356/156088

Internet

https://hdl.handle.net/10356/156088

Similar Items