CAFE: Coarse-to-Fine Neural Symbolic Reasoning for Explainable Recommendation

TL;DR

This paper introduces CAFE, a neural symbolic reasoning framework that uses coarse user profiles to guide fine-grained path finding in knowledge graphs, improving explainable recommendations.

Contribution

It proposes a novel coarse-to-fine reasoning approach with profile-guided path reasoning, enhancing recommendation accuracy and explainability in knowledge graph-based systems.

Findings

Substantial performance improvements over state-of-the-art methods

Effective use of user profiles for guiding reasoning paths

Scalable path-finding over large knowledge graphs

Abstract

Recent research explores incorporating knowledge graphs (KG) into e-commerce recommender systems, not only to achieve better recommendation performance, but more importantly to generate explanations of why particular decisions are made. This can be achieved by explicit KG reasoning, where a model starts from a user node, sequentially determines the next step, and walks towards an item node of potential interest to the user. However, this is challenging due to the huge search space, unknown destination, and sparse signals over the KG, so informative and effective guidance is needed to achieve a satisfactory recommendation quality. To this end, we propose a CoArse-to-FinE neural symbolic reasoning approach (CAFE). It first generates user profiles as coarse sketches of user behaviors, which subsequently guide a path-finding process to derive reasoning paths for recommendations as fine-grained predictions. User profiles can capture prominent user behaviors from the history, and provide valuable signals about which kinds of path patterns are more likely to lead to potential items of interest for the user. To better exploit the user profiles, an improved path-finding algorithm called Profile-guided Path Reasoning (PPR) is also developed, which leverages an inventory of neural symbolic reasoning modules to effectively and efficiently find a batch of paths over a large-scale KG. We extensively experiment on four real-world benchmarks and observe substantial gains in the recommendation performance compared with state-of-the-art methods.