FlavorDiffusion: Predicting Food Pairings and Chemical Interactions Using Diffusion Models

TL;DR

FlavorDiffusion introduces a diffusion-based machine learning framework that predicts food-chemical interactions and ingredient pairings, improving clustering and discovery of novel food combinations without chromatography.

Contribution

It is the first to apply diffusion models with graph embeddings and chemical encoding for food pairing prediction, achieving state-of-the-art performance in computational gastronomy.

Findings

Superior ingredient relationship reconstruction

State-of-the-art NMI scores in clustering

Enables discovery of novel ingredient combinations

Abstract

The study of food pairing has evolved beyond subjective expertise with the advent of machine learning. This paper presents FlavorDiffusion, a novel framework leveraging diffusion models to predict food-chemical interactions and ingredient pairings without relying on chromatography. By integrating graph-based embeddings, diffusion processes, and chemical property encoding, FlavorDiffusion addresses data imbalances and enhances clustering quality. Using a heterogeneous graph derived from datasets like Recipe1M and FlavorDB, our model demonstrates superior performance in reconstructing ingredient-ingredient relationships. The addition of a Chemical Structure Prediction (CSP) layer further refines the embedding space, achieving state-of-the-art NMI scores and enabling meaningful discovery of novel ingredient combinations. The proposed framework represents a significant step forward in computational gastronomy, offering scalable, interpretable, and chemically informed solutions for food science.