Multi-Modal Self-Supervised Learning Algorithm-Based Product Recommendation

With the rise of e-commerce, personalized recommendation algorithms have received much attention in recent years. Meanwhile, multimodal recommendation algorithms have become the next competitive track of personalized recommendation. The current mainstream recommendation algorithms (e.g., NeuMF, NGCF...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on automation science and engineering Ročník 22; s. 15371 - 15380
Hlavní autoři: Gao, Li, Fan, Haiping, Chen, Qingkui, Yang, Heyu
Médium: Journal Article
Jazyk:angličtina
Vydáno: IEEE 2025
Témata:
artificial intelligence
Collaborative filtering
Computational modeling
Data mining
Data models
Feature extraction
Motion pictures
Prediction algorithms
predictive models
Recommender system
Recommender systems
Self-supervised learning
Training
ISSN:1545-5955, 1558-3783
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:With the rise of e-commerce, personalized recommendation algorithms have received much attention in recent years. Meanwhile, multimodal recommendation algorithms have become the next competitive track of personalized recommendation. The current mainstream recommendation algorithms (e.g., NeuMF, NGCF) rely too much on empirical data and do not effectively utilize multimodal information to model user preferences, while there is the problem of sparsity of user preference data. Secondly, they are still limited to using the same weights to fuse the item features of different modalities, and have the problem of inaccurate recommendation. For this reason, this paper proposes Multi-Modal Self-Supervised Learning Algorithm Based Product Recommendation (MMSLRec). 1) Data augmentation by self-supervised adversarial perturbation generation learning is performed to supplement the missing interaction information of tailed products to solve the common data sparsity problem in product recommendation. 2) A multimodal representation learning module is introduced to capture deep features in image and text modalities using AlexNet and Bert, respectively, in order to avoid the recommendation accuracy degradation problem caused by insufficient data feature learning. 3) Learning the user's perceived strength in different modalities, using the user co-occurrence matrix to fuse the features and make recommendations. Experiments on Amazon-Electronics, Amazon-Clothing, and Amazon-Baby, with different degrees of data sparsity verify the effectiveness of our MMSLRec in solving the data sparsity problem and the multimodal user preference modeling problem, and compared to the state-of-the-art baseline recommendation model on the three datasets, the Recall@20 improved by 9.26%, 3.11% and 2.92%, respectively. Note to Practitioners-The motivation for this article arises from the requirement of efficient recommendation algorithms for e-commerce platforms. Mainstream recommendation algorithms are mainly based on sparse user item history interaction data for recommendation, which receives the limitation of data sparsity problem to a larger extent. Secondly, it is still limited to using the same weights to fuse the features of different modalities in the multimodal recommendation process. In this paper, we propose MMSLRec, which solves the data sparsity problem to a certain extent by using adversarial generative networks and fuse the features from different users using the user co-occurrence matrix. This method achieves better results in different applications.
ISSN:1545-5955
1558-3783
DOI:10.1109/TASE.2025.3568286