Neuro-Symbolic Recommendation Model based on Logic Query

TL;DR

This paper introduces a neuro-symbolic recommendation model that combines logic reasoning with neural networks to improve recommendation accuracy, especially under incomplete or inconsistent knowledge conditions.

Contribution

It proposes a novel approach transforming user interactions into logic expressions and using neural logic operations for reasoning in recommendations.

Findings

Outperforms state-of-the-art models on three datasets.

Effectively handles incomplete and inconsistent knowledge.

Reduces complexity of logic computation with an implicit encoder.

Abstract

A recommendation system assists users in finding items that are relevant to them. Existing recommendation models are primarily based on predicting relationships between users and items and use complex matching models or incorporate extensive external information to capture association patterns in data. However, recommendation is not only a problem of inductive statistics using data; it is also a cognitive task of reasoning decisions based on knowledge extracted from information. Hence, a logic system could naturally be incorporated for the reasoning in a recommendation task. However, although hard-rule approaches based on logic systems can provide powerful reasoning ability, they struggle to cope with inconsistent and incomplete knowledge in real-world tasks, especially for complex tasks such as recommendation. Therefore, in this paper, we propose a neuro-symbolic recommendation model, which transforms the user history interactions into a logic expression and then transforms the recommendation prediction into a query task based on this logic expression. The logic expressions are then computed based on the modular logic operations of the neural network. We also construct an implicit logic encoder to reasonably reduce the complexity of the logic computation. Finally, a user's interest items can be queried in the vector space based on the computation results. Experiments on three well-known datasets verified that our method performs better compared to state of the art shallow, deep, session, and reasoning models.