Sequential Recommendation with Probabilistic Logical Reasoning

TL;DR

This paper introduces SR-PLR, a neural-symbolic framework that combines deep neural networks with probabilistic logical reasoning to improve sequential recommendation by capturing uncertainty and evolving user preferences.

Contribution

The paper proposes a novel framework that integrates probabilistic logical reasoning with DNN-based SR models, enhancing their ability to model user behavior and uncertainty.

Findings

SR-PLR outperforms baseline models in recommendation accuracy.

Probabilistic reasoning improves modeling of user preference dynamics.

Framework effectively combines similarity matching with logical reasoning.

Abstract

Deep learning and symbolic learning are two frequently employed methods in Sequential Recommendation (SR). Recent neural-symbolic SR models demonstrate their potential to enable SR to be equipped with concurrent perception and cognition capacities. However, neural-symbolic SR remains a challenging problem due to open issues like representing users and items in logical reasoning. In this paper, we combine the Deep Neural Network (DNN) SR models with logical reasoning and propose a general framework named Sequential Recommendation with Probabilistic Logical Reasoning (short for SR-PLR). This framework allows SR-PLR to benefit from both similarity matching and logical reasoning by disentangling feature embedding and logic embedding in the DNN and probabilistic logic network. To better capture the uncertainty and evolution of user tastes, SR-PLR embeds users and items with a probabilistic method and conducts probabilistic logical reasoning on users' interaction patterns. Then the feature and logic representations learned from the DNN and logic network are concatenated to make the prediction. Finally, experiments on various sequential recommendation models demonstrate the effectiveness of the SR-PLR.