TY - JOUR
T1 - Distribution-aware hybrid noise augmentation in graph contrastive learning for recommendation
AU - Zhu, Kuiyu
AU - Qin, Tao
AU - Wang, Xin
AU - Liu, Zhaoli
AU - Wang, Chenxu
N1 - Publisher Copyright:
© 2024 Elsevier Ltd
PY - 2024/12/10
Y1 - 2024/12/10
N2 - The recommender systems are one of the most effective big data tools for solving the information overload problem, but data sparsity greatly affects its performance. However, most of the existing graph-based contrastive learning methods perturb the original graph structure for data augmentation, which may lead to semantic loss and subsequently degrade the recommendation performance. Meanwhile, studies have shown that improving the uniformity of data distribution is more effective than data augmentation using graph perturbation. In this paper, to enhance the uniformity of data distribution, we propose Distribution-Aware Hybrid Noise augmentation in graph contrastive learning for Recommendation (DAHNRec). Specifically, we design distribution-aware hybrid noise augmentation (DAHN) method to generate noise suitable for the users and items, instead of simply utilizing random noise following uniform distributions. By applying DAHN, the model can learn the appropriate noise distribution during the training process to enhance the uniformity of the embedding space. Additionally, we propose Balanced Bayesian Personalized Ranking (BBPR) as the loss function for recommendation tasks to improve difference characterizing between positive and negative samples. This improves the ranking tasks’ performance. Furthermore, we conduct extensive experiments based on public benchmark datasets. The results indicate that DAHNRec outperforms several existing methods. Furthermore, DAHNRec is a general recommendation model based on user–item interactions, which can be used to improve the recommendation performance in various real-world scenarios, such as e-commerce platforms and social media.
AB - The recommender systems are one of the most effective big data tools for solving the information overload problem, but data sparsity greatly affects its performance. However, most of the existing graph-based contrastive learning methods perturb the original graph structure for data augmentation, which may lead to semantic loss and subsequently degrade the recommendation performance. Meanwhile, studies have shown that improving the uniformity of data distribution is more effective than data augmentation using graph perturbation. In this paper, to enhance the uniformity of data distribution, we propose Distribution-Aware Hybrid Noise augmentation in graph contrastive learning for Recommendation (DAHNRec). Specifically, we design distribution-aware hybrid noise augmentation (DAHN) method to generate noise suitable for the users and items, instead of simply utilizing random noise following uniform distributions. By applying DAHN, the model can learn the appropriate noise distribution during the training process to enhance the uniformity of the embedding space. Additionally, we propose Balanced Bayesian Personalized Ranking (BBPR) as the loss function for recommendation tasks to improve difference characterizing between positive and negative samples. This improves the ranking tasks’ performance. Furthermore, we conduct extensive experiments based on public benchmark datasets. The results indicate that DAHNRec outperforms several existing methods. Furthermore, DAHNRec is a general recommendation model based on user–item interactions, which can be used to improve the recommendation performance in various real-world scenarios, such as e-commerce platforms and social media.
KW - Data distribution
KW - Graph contrastive learning
KW - Noise augmentation
KW - Recommender systems
UR - https://www.scopus.com/pages/publications/85201392232
U2 - 10.1016/j.eswa.2024.125118
DO - 10.1016/j.eswa.2024.125118
M3 - 文章
AN - SCOPUS:85201392232
SN - 0957-4174
VL - 257
JO - Expert Systems with Applications
JF - Expert Systems with Applications
M1 - 125118
ER -