Visually-aware Collaborative Food Recommendation.

Food recommender systems play an important role in assisting users to identify the desired food to eat. Deciding what food to eat is a complex and multi-faceted process, which is influenced by many factors such as the ingredients, appearance of the recipe, the useru0027s personal preference on food, and various contexts like what had been eaten in the past meals. In this work, we formulate the food recommendation problem as predicting user preference on recipes based on three key factors that determine a useru0027s choice on food, namely, 1) the useru0027s (and other usersu0027) history; 2) the ingredients of a recipe; and 3) the descriptive image of a recipe. To address this challenging problem, we develop a dedicated neural network based solution Hierarchical Attention based Food Recommendation (HAFR) which is capable of: 1) capturing the collaborative filtering effect like what similar users tend to eat; 2) inferring a useru0027s preference at the ingredient level; and 3) learning user preference from the recipeu0027s visual images. To evaluate our proposed method, we construct a large-scale dataset consisting of millions of ratings from AllRecipes.com. Extensive experiments show that our method outperforms several competing recommender solutions like Factorization Machine and Visual Bayesian Personalized Ranking with an average improvement of 12%, offering promising results in predicting user preference for food. Codes and dataset will be released upon acceptance.