Learning over Knowledge-Base Embeddings for Recommendation

By Qingyao Ai, Vahid Azizi, Xu Chen, Yongfeng Zhang. 2018

379 citations recorded by the source corpus.

Providing model-generated explanations in recommender systems is important to user experience. State-of-the-art recommendation algorithms—especially the collaborative filtering (CF)- based approaches with shallow or deep models—usually work with various unstructured information sources for recommendation, such as textual reviews, visual images, and various implicit or explicit feedbacks. Though structured knowledge bases were considered in content-based approaches, they have been largely ignored recently due to the availability of vast amounts of data and the learning power of many complex models. However, structured knowledge bases exhibit unique advantages in personalized recommendation systems. When the explicit knowledge about users and items is considered for recommendation, the system could provide highly customized recommendations based on users’ historical behaviors and the knowledge is helpful for providing informed explanations regarding the recommended items. A great challenge for using knowledge bases for recommendation is how to integrate large-scale structured and unstructured data, while taking advantage of collaborative filtering for highly accurate performance. Recent achievements in knowledge-base embedding (KBE) sheds light on this problem, which makes it possible to learn user and item representations while preserving the structure of their relationship with external knowledge for explanation. In this work, we propose to explain knowledge-base embeddings for explainable recommendation. Specifically, we propose a knowledge-base representation learning framework to embed heterogeneous entities for recommendation, and based on the embedded knowledge base, a soft matching algorithm is proposed to generate personalized explanations for the recommended items. Experimental results on real-world e-commerce datasets verified the superior recommendation performance and the explainability power of our approach compared with state-of-the-art baselines.

Subfields: Artificial Intelligence, Information Systems

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. Xiangnan He
2. Xiang Wang
3. Tat-seng Chua
4. Xu Chen
5. Yongfeng Zhang
6. Yong Li
7. Chen Gao
8. Xing Xie

In Information Systems

1. Xiangnan He
2. Xiang Wang
3. Yongfeng Zhang
4. Tat-seng Chua
5. Xu Chen
6. Xing Xie
7. Le Wu
8. Yong Li

Citations in the corpus

• Reinforcement Knowledge Graph Reasoning for Explainable Recommendation (2019, methodology): “ce and uncover the similarity between entities by calculating their representation distance [30]. However, pure KG embedding methods lack the ability to discover multi-hop relational paths. Ai et al. [1] proposed to enhance the collaborative filtering (CF) method over KG embedding for personalized r”
• Incorporating Interpretability into Latent Factor Models via Fast Influence Analysis (2018, background): “Existing works on enhancing recommender systems with interpretability can be classified into different categories based on the type of recommendation models, including latent factor models [1, 3, 23, 26, 39], memory-based models [29, 32], graph-based models [5, 15, 35], deep learning models [8, 24, ”
• AliCoCo: Alibaba E-commerce Cognitive Concept Net (2020, methodology): “Inspired by the construction of opendomain KGs, different kinds of KGs in e-commerce are constructed to describe relations among users, items and item attributes [1, 6].”
• KGAT: Knowledge Graph Attention Network for Recommendation (2019, methodology): “As we can see, KGAT achieves comparable computation complexity to SL models (FM and NFM) and regularization-based methods (CFKG and CKE), being much efficient that path-based methods (MCRec and RippleNet).”
• Unifying Knowledge Graph Learning and Recommendation: Towards a Better Understanding of User Preferences (2019, methodology): “eath Becomes Her, if there exist some users who like the movie also have a preference of other movies directed by Robert Zemeckis. Although many prior efforts have leveraged KG in recommender systems [16, 29, 30, 44, 46, 48], there are few works that jointly arXiv:1902.06236v1 [cs.IR] 17 Feb 2019 É ”
• Learning Intents behind Interactions with Knowledge Graph for Recommendation (2021, methodology): “GNN-based Methods [17, 38, 39, 41, 47] are founded upon the information aggregation mechanism of graph neural networks (GNNs) [13, 14, 19, 34, 42].”
• A Survey on Knowledge Graph-Based Recommender Systems (2020, background): “Zhang et al. [13] proposed CFKG, which constructs a user-item KG.”
• A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions (2021, methodology): “The main concern in this stage is to consider multiple relationships among the top-scored items [5, 255].”
• Graph Neural Networks in Recommender Systems: A Survey (2020, methodology): “Previous works preprocess knowledge graph by knowledge graph embedding (KGE) methods to learn the embeddings of entities and relations, such as [26, 146, 196, 202] The limitation of commonly-used KGE methods is that they focus on modeling rigorous semantic relatedness with the transition constraint,”
• Personalized Fashion Recommendation with Visual Explanations based on Multimodal Attention Network: Towards Visually Explainable Recommendation (2019, background): “ECFKG [1] borrowed the idea from translationbased objective function to build a personalization model based on multiple item relationships.”
• A Reinforcement Learning Framework for Explainable Recommendation (2018, background): “Instead of refining existing recommendation models, researchers have also built inherently more explainable models by using intuitive data structures such as graphs [10], decision trees [31], and knowledge bases [32], [33].”
• Riker: Mining Rich Keyword Representations for Interpretable Product Question Answering (2019, background): “On the application level, people have explored making systems more interpretable to users including recommendation systems [2], visual QA [32], multiple choice answers [40] and so on.”
• A historical perspective of explainable Artificial Intelligence (2020, methodology): “…decomposition (SVD; Nati & Jaakkola, 2003) or nonnegative matrix factorisation (NMF; Lee & Seung, 1999), Nearest Neighbors, and methods based on embeddings such as Deep Learning (Wang, He, Feng, Nie, & Chua, 2018) or Knowledge-based Embeddings for Recommendation (Zhang, Ai, Chen, & Wang, 2018).”