Multi-modal Knowledge Graphs for Recommender Systems

By Rui Sun, Xuezhi Cao, Yan Zhao, Juncheng Wan, Kun Zhou, Fuzheng Zhang, Zhongyuan Wang, Kai Zheng. International Conference on Information and Knowledge Management, 2020

337 citations recorded by the source corpus.

Recommender systems have shown great potential to solve the information explosion problem and enhance user experience in various online applications. To tackle data sparsity and cold start problems in recommender systems, researchers propose knowledge graphs (KGs) based recommendations by leveraging valuable external knowledge as auxiliary information. However, most of these works ignore the variety of data types (e.g., texts and images) in multi-modal knowledge graphs (MMKGs). In this paper, we propose Multi-modal Knowledge Graph Attention Network (MKGAT) to better enhance recommender systems by leveraging multi-modal knowledge. Specifically, we propose a multi-modal graph attention technique to conduct information propagation over MMKGs, and then use the resulting aggregated embedding representation for recommendation. To the best of our knowledge, this is the first work that incorporates multi-modal knowledge graph into recommender systems. We conduct extensive experiments on two real datasets from different domains, results of which demonstrate that our model MKGAT can successfully employ MMKGs to improve the quality of recommendation system.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Information Systems

View Paper: https://www.semanticscholar.org/paper/a6da5335dc3be1aac689ce5393c8e187fcef083d

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Feng Xia
2. Yue Liu
3. Siwei Wang
4. Zhixu Li
5. Lingyuan Meng
6. Wenxuan Tu
7. Linhao Luo
8. Fei Sun

In Computer Vision and Pattern Recognition

1. Yue Liu
2. Siwei Wang
3. Zhixu Li
4. Wenxuan Tu
5. Fei Sun
6. Penglei Sun
7. Bin Cui
8. Xindong Wu

In Information Systems

1. Linhao Luo
2. Fei Sun
3. Bin Cui
4. Xindong Wu
5. Shiwen Wu
6. Fei Sun
7. Nicholas Jing Yuan
8. Chen Chen

Citations in the corpus

• Unifying Large Language Models and Knowledge Graphs: A Roadmap (2023, background): “These knowledge graphs can be used for various multi-modal tasks such as image-text matching [87], visual question answering [88], and recommendation [89].”
• Graph Neural Networks in Recommender Systems: A Survey (2020, background): “MKGAT [134] unifies the user nodes and multi-modal knowledge graph into one graph and employs a relation-aware graph attention network to propagate information.”
• Knowledge Graphs: Opportunities and Challenges (2023, background): “They are also widely applied in many fields (e.g., education and medical care) to benefit human life and society (Sun et al. 2020; Bounhas et al. 2020).”
• A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multi-Modal (2022, background): “MKGAT [254] better enhances recommendation systems with a multi-modal graph attention technique to conduct information propagation over multi-modal KGs. KB-VQA [255] and VSUA [256] perform reasoning on the image and external knowledge, which provides an intuitive way to explain the generated answers”
• Multi-Modal Knowledge Graph Construction and Application: A Survey (2022, background): “Differently, some recent efforts [131], [168] novelly proposes to construct a personalized MMKG from the images and texts of items in various ways, and then the entity relation reasoning between items can be better modeled by taking the relations in MMKG into account.”
• A Survey on Accuracy-Oriented Neural Recommendation: From Collaborative Filtering to Information-Rich Recommendation (2021, neutral): “[178], [179], and GNN-based approaches [97], [128], [141], [170], [180], [181], [182], [183], [184], [185], [186], [187].”