An IEEE study introduces a new recommendation model that combines knowledge graphs and contrastive learning to solve cold-start and sparse data issues.
-- A newly published study from the Institute of Electrical and Electronics Engineers (IEEE) presents a novel approach to improving the accuracy and robustness of recommender systems, using a combination of knowledge graph embedding, two-dimensional convolutional models, and contrastive learning. The research offers an effective solution to long-standing issues in personalization technologies, including data sparsity and the cold-start problem.
The paper, titled "Research on the Application of Knowledge Graph-Driven Two-Dimensional Convolutional Embedding Methods in Recommender Systems”, was presented at the 2025 International Conference on Intelligent Systems and Computational Networks (ICISCN).
The study proposes a framework that extracts user preferences from interaction graphs and item features from knowledge graphs. A two-dimensional convolutional model, incorporating spatial and channel attention, is used to enhance feature extraction from the item side. Recommendation predictions are made through inner product operations between user and item vectors.
To further improve performance in real-world settings where data may be noisy or incomplete, the study introduces a contrastive learning strategy. By generating augmented subgraphs and comparing them to the original knowledge graph, the system learns hierarchical features that enhance both the accuracy and stability of recommendations.
"Real-world recommendation systems are often challenged by incomplete or noisy data,” said lead author Peng Dong. "Our goal was to build a model that not only improves accuracy, but also stays reliable under real-world constraints.”
This motivation led to the development of two models—KG-UIR and KGCRL—evaluated on multiple benchmarks. Results showed marked improvements in recommendation accuracy and a measurable reduction in the negative impact of cold-start and sparse-data scenarios.
The research could be applied widely in industries where personalized user engagement is critical, including e-commerce, streaming media, digital advertising, and financial services. Systems built on this architecture could enable more relevant product suggestions, smarter content delivery, and more effective user targeting.
Peng Dong, the paper's lead author, holds a master's degree in Business Intelligence and Analytics – Data Science Concentration from Stevens Institute of Technology. He has worked on large-scale recommendation and predictive modeling systems at companies such as Paramount and The Trade Desk. His broader research spans areas including interpretable AI, financial risk modeling, and the impact of corporate ownership structures on long-term financial sustainability.
The paper, presented at the 2025 International Conference on Intelligent Systems and Computational Networks and published by the IEEE, is available via the IEEE Xplore digital library.
Contact Info:
Name: Peng Dong
Email: Send Email
Organization: Peng Dong
Website: https://scholar.google.com/citations?hl=en&user=9lstaOsAAAAJ
Release ID: 89157655
If you come across any problems, discrepancies, or concerns related to the content contained within this press release that necessitate action or if a press release requires takedown, we strongly encourage you to reach out without delay by contacting [email protected] (it is important to note that this email is the authorized channel for such matters, sending multiple emails to multiple addresses does not necessarily help expedite your request). Our committed team will be readily accessible round-the-clock to address your concerns within 8 hours and take appropriate actions to rectify identified issues or support with press release removals. Ensuring accurate and reliable information remains our unwavering commitment.