NutriGNN: Food Nutrient Prediction with an LLM Enriched Knowledge Graph
Posted 2025
Abstract
A graph neural network approach to predicting missing nutrient values in food composition databases. By building a knowledge graph enriched with LLM-derived semantic relations between foods, NutriGNN improves representation learning and prediction quality, especially for low-resource food items with sparse nutritional data.
Recommended citation: Lesner, J., & Anand, S. (2025). Technical Report.
Download Paper