Robust Preference-Guided Based Disentangled Graph Social Recommendation

• Published in: IEEE transactions on network science and engineering Vol. 11; no. 5; pp. 4898 - 4910
• Main Authors: Ma, Gang-Feng, Yang, Xu-Hua, Zhou, Yanbo, Long, Haixia, Huang, Wei, Gong, Weihua, Liu, Sheng
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.09.2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Disentangled preference representation; Graph neural networks; Preferences; Recommender systems; Representations; Robustness; Self-supervised learning; Social networking (online); Social networks; social recommendation; Supervised learning; Training; Vectors

Social recommendations introduce additional social information to capture users' potential item preferences, thereby providing more accurate recommendations. However, friends do not always have the same or similar preferences, which means that social information is redundant and often biased fo...