Personalized Food Recommendation as Constrained Question Answering over a Large-scale Food Knowledge Graph

  title={Personalized Food Recommendation as Constrained Question Answering over a Large-scale Food Knowledge Graph},
  author={Yu Chen and Ananya Subburathinam and Ching-Hua Chen and Mohammed J. Zaki},
  journal={Proceedings of the 14th ACM International Conference on Web Search and Data Mining},
Food recommendation has become an important means to help guide users to adopt healthy dietary habits. Previous works on food recommendation either i) fail to consider users' explicit requirements, ii) ignore crucial health factors (e.g., allergies and nutrition needs), or iii) do not utilize the rich food knowledge for recommending healthy recipes. To address these limitations, we propose a novel problem formulation for food recommendation, modeling this task as constrained question answering… 

Figures and Tables from this paper

Self-supervised Calorie-aware Heterogeneous Graph Networks for Food Recommendation

A Self-supervised Calorie-aware Heterogeneous Graph Network (SCHGN) is proposed to model the relations between ingredients and incorporate calories of food simultaneously and captures users’ dynamic preferences on calories offood.

Learning Personal Food Preferences via Food Logs Embedding

This work proposes a method for learning food preferences from food logs, a comprehensive but noisy source of information about users’ dietary habits that identifies 82% of a user’s ten most frequently eaten foods.

Web Semantics: Science, Services and Agents on the World Wide Web

This paper introduces health-guided recipe recommendation as a way to incrementally shift users towards healthier recipe options while respecting the preferences reflected in their past choices.

Personal Health Knowledge Graph for Clinically Relevant Diet Recommendations

It is discussed how lifestyle guidelines grounded in semantic technologies can be reasoned with the generated personal health knowledge graph to provide appropriate dietary recommendations that satisfy the user’s medical and other lifestyle needs.

Food Knowledge Representation Learning with Adversarial Substitution

This work employs a pre-trained language model to encode entities and relations over a food knowledge graph, thus emphasizing contextual information in food KGs, and proposes multiple strategies to generate high quality context-aware recipe and ingredient substitutions.

Towards Building a Food Knowledge Graph for Internet of Food

This comprehensive summary of current research on food knowledge graphs shows that food knowledge graph play an important role in food-oriented applications, including food search and Question Answering, personalized dietary recommendation, food analysis and visualization, food traceability, and food machinery intelligent manufacturing.

Applications of knowledge graphs for food science and industry

Improving embedded knowledge graph multi-hop question answering by introducing relational chain reasoning

An extensive empirical study on three open-domain benchmarks proves that the proposed Relational Chain based Embedded KGZA (Rce-KGQA) method significantly outperforms the state-of-the-art counterparts like GraftNet, PullNet and EmbedKG QA.

VRKG4Rec: Virtual Relational Knowledge Graphs for Recommendation

A VRKG4Rec model (Virtual Relational Knowledge Graphs for Recommendation), which clusters relations with latent relevance to generates virtual relations, is proposed, which outperforms the state-of-the-art methods.

Using Knowledge Graph Embeddings in Embedding Based Recommender Systems

It is shown that the suggested replacement improves the representation learning of the embedding layer by adding a semantic layer that can increase the overall performance of the normal embedding based recommenders.



Yum-Me: A Personalized Nutrient-Based Meal Recommender System

Yum-me is proposed, a personalized nutrient-based meal recommender system designed to meet individuals’ nutritional expectations, dietary restrictions, and fine-grained food preferences, and a novel online learning framework that learns food preference from itemwise and pairwise image comparisons.

Food Recommender Systems: Important Contributions, Challenges and Future Research Directions

A summary of the state-of-the-art of so-called food recommender systems is provided, highlighting both seminal and most recent approaches to the problem, as well as important specializations, such as food recommendation systems for groups of users or systems which promote healthy eating.

FoodKG: A Semantics-Driven Knowledge Graph for Food Recommendation

This work describes the construction process of the knowledge graph, the plan for its maintenance, and how this knowledge graph has been utilized in several applications, including a SPARQL-based service that lets a user determine what recipe to make based on ingredients at hand while taking constraints such as allergies into account.

FoodKG Enabled Q&A Application

The FoodKG, a food knowledge graph designed to assist in food recommendation, is used to power a cognitive agent that performs knowledge-base question answering, primarily to help improve peoples' diets by guiding them towards better foods.

Food Recommendation: Framework, Existing Solutions, and Challenges

This article proposes a unified framework for food recommendation, and identifies main issues affecting food recommendation including incorporating various context and domain knowledge, building the personal model, and analyzing unique food characteristics.

Food Recommendation Using Ontology and Heuristics

It is concluded that semantic recommender systems in general outperform traditional recommenders systems with respect to accuracy, precision, and recall, and that the proposed recommender has a better F-measure than existing semantic recommenders.

Health-aware Food Recommender System

This demo paper summarizes the complete human-computer interaction design, the implemented health-aware recommendation algorithm, and preliminary user feedback of the recommender system developed on a mobile platform.

Adapting recommender systems to the requirements of personal health record systems

A ranking procedure based on the health graph is outlined which enables a match between entries of aPHR system and health information artifacts and this way a PHR user will obtain individualized health information he might be interested in.

Recipe Recommendation Method by Considering the User's Preference and Ingredient Quantity of Target Recipe

In order to reflect the truly user's preferences, this work proposes a scoring method of cooking recipes based on user's food preferences and the quantity of the ingredient in a recipe.

Billion-scale Commodity Embedding for E-commerce Recommendation in Alibaba

The technical solutions to address the scalability, sparsity and cold start problems of RS in Taobao are presented, and two aggregation methods to integrate the embeddings of items and the corresponding side information are proposed.