Cross-View Heterogeneous Graph Contrastive Learning Method for Healthy Food Recommendation

Exploring food’s rich composition and nutritional information is crucial for understanding and improving people’s dietary preferences and health habits. However, most existing food recommendation models tend to overlook the impact of food choices on health. Moreover, due to the high sparsity of food-related data, most existing methods fail to effectively leverage the multi-dimensional information of food, resulting in poorly learned node embeddings. Considering these factors, we propose a cross-view contrastive heterogeneous-graph learning method for healthy food recommendation (CGHF). Specifically, CGHF constructs feature relation graphs and heterogeneous information connection graphs by integrating user–food interaction data and multi-dimensional information about food. We then design a cross-view contrastive learning task to learn node embeddings from multiple views collaboratively. Additionally, we introduce a meta-path-based local aggregation mechanism to aggregate node information in local subgraphs, thus allowing for the efficient capturing of users’ dietary preferences. Experimental comparisons with various advanced models demonstrate the effectiveness of the proposed model.