Jointly Learning Explainable Rules for Recommendation with Knowledge Graph

By Weizhi Ma, Min Zhang, Woojeong Jin, Chenyang Wang, Yiqun Liu, Shaoping Ma, Xiang Ren. 2019

246 citations recorded by the source corpus.

Explainability and effectiveness are two key aspects for building recommender systems. Prior efforts mostly focus on incorporating side information to achieve better recommendation performance. However, these methods have some weaknesses: (1) prediction of neural network-based embedding methods are hard to explain and debug; (2) symbolic, graph-based approaches (e.g., meta path-based models) require manual efforts and domain knowledge to define patterns and rules, and ignore the item association types (e.g. substitutable and complementary). In this paper, we propose a novel joint learning framework to integrate induction of explainable rules from knowledge graph with construction of a rule-guided neural recommendation model. The framework encourages two modules to complement each other in generating effective and explainable recommendation: 1) inductive rules, mined from item-centric knowledge graphs, summarize common multi-hop relational patterns for inferring different item associations and provide human-readable explanation for model prediction; 2) recommendation module can be augmented by induced rules and thus have better generalization ability dealing with the cold-start issue. Extensive experiments1 show that our proposed method has achieved significant improvements in item recommendation over baselines on real-world datasets. Our model demonstrates robust performance over “noisy” item knowledge graphs, generated by linking item names to related entities.

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. Yong Li
3. Chen Gao
4. Depeng Jin
5. Xing Xie
6. Fei Sun
7. Bin Cui
8. Shiwen Wu

In Information Systems

1. Xiangnan He
2. Yong Li
3. Chen Gao
4. Xing Xie
5. Depeng Jin
6. Fei Sun
7. Bin Cui
8. Shiwen Wu

Citations in the corpus

• Learning Intents behind Interactions with Knowledge Graph for Recommendation (2021, unknown): “Embedding-based Methods [1, 4, 16, 35, 37, 51] focus mainly on the first-order connectivity (i.e., user-item pairs in interaction data, triplets in KG), hire KG embedding techniques (e.g., TransE [3] and TransH [46]) to learn entity embeddings, and then use them as prior or context information of it”
• A Survey on Knowledge Graph-Based Recommender Systems (2020, background): “…[79] CIKM 2015 ProPPR [80] RecSys 2016 FMG [3] KDD 2017 MCRec [1] KDD 2018 RKGE [81] RecSys 2018 HERec [82] TKDE 2019 KPRN [83] AAAI 2019 RuleRec [84] WWW 2019 PGPR [85] SIGIR 2019 EIUM [86] MM 2019 Ekar [87] arXiv 2019 RippleNet [14] CIKM 2018 RippleNet-agg [88] TOIS 2019 KGCN [89] WWW 2019…”
• A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions (2021, methodology): “Model Network Design Source of Explainability ECFKG [5] Meta-path based GE Meta-path over knowledge graph RippleNet [171] Meta-path based GraphSage Meta-path over knowledge graph EIUM [75] Meta-path based GE Meta-path over knowledge graph KPRN [185] Meta-path based GE Meta-path over knowledge graph ”
• When large language models meet personalization: perspectives of challenges and opportunities (2023, unknown): “Path-based approaches, such as Hete-MF [44], SemRec [45], RuleRec [46], EIUM [47], exploit the semantic connectivity information present in the knowledge graph to regularize the user and item representations.”
• Graph Neural Networks in Recommender Systems: A Survey (2020, background): “There are also some attempts on explainability on GNN-based recommendation [63, 107, 156].”
• Distilling Structured Knowledge into Embeddings for Explainable and Accurate Recommendation (2019, background): “incorporate social relations for better explanations. Catherine et al. [3] leverage knowledge graphs to generate recommendations together with their explanations with Personalized PageRank. Ma et al. [22] exploits induced rules from knowledge graphs for more explainablility. We can see that most of ”