Popularity-Debiased Graph Self-Supervised for Recommendation
-
Published:2024-02-06
Issue:4
Volume:13
Page:677
-
ISSN:2079-9292
-
Container-title:Electronics
-
language:en
-
Short-container-title:Electronics
Author:
Li Shanshan12ORCID, Hu Xinzhuan3, Guo Jingfeng12, Liu Bin4, Qi Mingyue45, Jia Yutong12
Affiliation:
1. College of Information Science and Engineering, Yanshan University, Qinhuangdao 066004, China 2. The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province, Qinhuangdao 066004, China 3. School of Economics and Management, Yanshan University, Qinhuangdao 066004, China 4. The Big Data and Social Computing Research Center, Hebei University of Science and Technology, Shijianzhuang 050018, China 5. Hebei Reading Information Technology Co., Ltd., Shijiazhuang 050000, China
Abstract
The rise of graph neural networks has greatly contributed to the development of recommendation systems, and self-supervised learning has emerged as one of the most important approaches to address sparse interaction data. However, existing methods mostly focus on the recommendation’s accuracy while neglecting the role of recommended item diversity in enhancing user interest and merchant benefits. The reason for this phenomenon is mainly due to the bias of popular items, which makes the long-tail items (account for a large proportion) be neglected. How to mitigate the bias caused by item popularity has become one of the hot topics in current research. To address the above problems, we propose a Popularity-Debiased Graph Self-Supervised for Recommendation (PDGS). Specifically, we apply a penalty constraint on item popularity during the data enhancement process on the user–item interaction graph to eliminate the inherent popularity bias. We generate item similarity graphs with the popularity bias removed to construct a self-supervised learning task under multiple views, and we design model optimization strategies from the perspectives of popular items and long-tail items to generate recommendation lists. We conduct a large number of comparison experiments, as well as ablation experiments, on three public datasets to verify the effectiveness and the superiority of the model in balancing recommendation accuracy and diversity.
Funder
S&T Program of Hebei National Natural Science Foundation of China National Cultural and Tourism Science and Technology Innovation Project (2020), Hebei Natural Science Foundation
Subject
Electrical and Electronic Engineering,Computer Networks and Communications,Hardware and Architecture,Signal Processing,Control and Systems Engineering
Reference39 articles.
1. Lian, J., Zhou, X., Zhang, F., Chen, Z., Xie, X., and Sun, G. (2018, January 19–23). xdeepfm: Combining explicit and implicit feature interactions for recommender systems. Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, London, UK. 2. Lin, Z., Tian, C., Hou, Y., and Zhao, W.X. (2022, January 25–29). Improving graph collaborative filtering with neighborhood-enriched contrastive learning. Proceedings of the ACM Web Conference 2022, Lyon, France. 3. Abdollahpouri, H. (2019, January 27–28). Popularity bias in ranking and recommendation. Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society, Honolulu, HI, USA. 4. Saito, Y., Yaginuma, S., Nishino, Y., Sakata, H., and Nakata, K. (2020, January 3–7). Unbiased recommender learning from missing-not-at-random implicit feedback. Proceedings of the 13th International Conference on Web Search and Data Mining, Houston, TX, USA. 5. Bias and debias in recommender system: A survey and future directions;Chen;ACM Trans. Inf. Syst.,2023
|
|