Faithfully Explainable Recommendation via Neural Logic Reasoning

Abstract

Knowledge graphs (KG) have become increasingly important to endow modern recommender systems with the ability to generate traceable reasoning paths to explain the recommendation process. However, prior research rarely considers the faithfulness of the derived explanations to justify the decision making process. To the best of our knowledge, this is the first work that models and evaluates faithfully explainable recommendation under the framework of KG reasoning. Specifically, we propose neural logic reasoning for explainable recommendation (LOGER) by drawing on interpretable logical rules to guide the path reasoning process for explanation generation. We experiment on three large-scale datasets in the e-commerce domain, demonstrating the effectiveness of our method in delivering high-quality recommendations as well as ascertaining the faithfulness of the derived explanation.

arXiv commentAccepted in NAACL 2021

References in corpus (8)

• A Survey on Knowledge Graphs: Representation, Acquisition and Applications
• KGAT: Knowledge Graph Attention Network for Recommendation
• Learning over Knowledge-Base Embeddings for Recommendation
• Learning Heterogeneous Knowledge Base Embeddings for Explainable Recommendation
• CAFE: Coarse-to-Fine Neural Symbolic Reasoning for Explainable Recommendation
• Neural-Symbolic Reasoning over Knowledge Graph for Multi-stage Explainable Recommendation
• COOKIE: A Dataset for Conversational Recommendation over Knowledge Graphs in E-commerce
• Faithful Multimodal Explanation for Visual Question Answering