Chao Zheng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Chao Zheng has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Bin Liu
School of economics and management, Hebei University of Science and Technology, Shijiazhuang 050018, China
1 shared publication - Jingfeng Guo
College of Information Science and Engineering, Yanshan University, Qinhuangdao, China
1 shared publication - Shanshan Li
College of Information Science and Engineering, Yanshan University, Qinhuangdao 066004, China
1 shared publication - Yutong Jia
College of Information Science and Engineering, Yanshan University, Qinhuangdao 066004, China
1 shared publication
Latest Publications
- Open Access
- 23 August 2022
- Published by MDPI AG in Mathematics
- Vol. 10 (17) , 3042
BiInfGCN: Bilateral Information Augmentation of Graph Convolutional Networks for Recommendation
The current graph-neural-network-based recommendation algorithm fully considers the interaction between users and items. It achieves better recommendation results, but due to a large amount of data, the interaction between users and items still suffers from the problem of data sparsity. To address this problem, we propose a method to alleviate the data sparsity problem by retaining user–item interactions while fully exploiting the association relationships between items and using side-information enhancement. We constructed a “twin-tower” model by combining a user–item training model and an item–item training model inspired by the knowledge distillation technique; the two sides of the structure learn from each other during the model training process. Comparative experiments were carried out on three publicly available datasets, using the recall and the normalized discounted cumulative gain as evaluation metrics; the results outperform existing related base algorithms. We also carried out extensive parameter sensitivity and ablation experiments to analyze the influence of various factors on the model. The problem of user–item interaction data sparsity is effectively addressed.
- 23 August 2022
- Published by MDPI AG in Mathematics
- Vol. 10 (17) , 3042
Open AccessBiInfGCN: Bilateral Information Augmentation of Graph Convolutional Networks for Recommendation
The current graph-neural-network-based recommendation algorithm fully considers the interaction between users and items. It achieves better recommendation results, but due to a large amount of data, the interaction between users and items still suffers from the problem of data sparsity. To address this problem, we propose a method to alleviate the data sparsity problem by retaining user–item interactions while fully exploiting the association relationships between items and using side-information enhancement. We constructed a “twin-tower” model by combining a user–item training model and an item–item training model inspired by the knowledge distillation technique; the two sides of the structure learn from each other during the model training process. Comparative experiments were carried out on three publicly available datasets, using the recall and the normalized discounted cumulative gain as evaluation metrics; the results outperform existing related base algorithms. We also carried out extensive parameter sensitivity and ablation experiments to analyze the influence of various factors on the model. The problem of user–item interaction data sparsity is effectively addressed.