Jointly Learning Explainable Rules for Recommendation with Knowledge Graph

TLDR

Recommender systems must balance explainability and effectiveness, yet existing approaches either rely on side information with opaque neural embeddings or on manually crafted symbolic rules that ignore item association types. This work proposes a joint learning framework that induces explainable rules from a knowledge graph and integrates them into a rule‑guided neural recommendation model. The framework comprises two complementary modules: an inductive rule miner that extracts multi‑hop relational patterns from item‑centric knowledge graphs to provide human‑readable explanations, and a recommendation module that incorporates these rules to improve generalization, especially for cold‑start items. Experiments on real‑world datasets demonstrate that the proposed method significantly outperforms baselines and remains robust even when the knowledge graph is noisy.

Abstract

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.