Enhanced Social Recommendation Method Integrating Rating Bias Offsets
Current social recommendations based on Graph Neural Networks (GNNs) often neglect to extract rating bias from user and item statistics, leading to misinterpreting real user preferences. For example, a high rating from a user with lenient rating standards and a high average rating does not always in...
Main Authors: | Lu Han, Jiwei Qin, Boshen Xia |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-09-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/12/18/3926 |
Similar Items
-
Fusion of Personalized Implicit Relations for Social Recommendation
by: Wei Qin, et al.
Published: (2024-01-01) -
Attention-Enhanced Graph Neural Networks With Global Context for Session-Based Recommendation
by: Yingpei Chen, et al.
Published: (2023-01-01) -
Knowledge-Aware Enhanced Network Combining Neighborhood Information for Recommendations
by: Xiaole Wang, et al.
Published: (2023-04-01) -
Graph Neural Network Recommendation Model Integrating User Preferences
by: XIONG Zhong-min, SHU Gui-wen, GUO Huai-yu
Published: (2022-06-01) -
Temporal attention graph-optimized networks for sequential recommendation
by: Pathak, Siddhant
Published: (2024)