Knowledge Graph-based Session Recommendation with Adaptive Propagation

TL;DR

This paper introduces a novel session recommendation method that uses a knowledge graph with multi-typed edges and adaptive neighbor aggregation to better capture user intentions across sessions, improving recommendation accuracy.

Contribution

It proposes a knowledge graph with multi-typed edges and session-adaptive propagation, addressing limitations of previous methods in capturing global item information and session-specific intentions.

Findings

Improves session recommendation accuracy by 10%-20%.

Achieves a 2% performance boost in an industrial case study.

Enhances existing models with knowledge graph and adaptive propagation.

Abstract

Session-based recommender systems (SBRSs) predict users' next interacted items based on their historical activities. While most SBRSs capture purchasing intentions locally within each session, capturing items' global information across different sessions is crucial in characterizing their general properties. Previous works capture this cross-session information by constructing graphs and incorporating neighbor information. However, this incorporation cannot vary adaptively according to the unique intention of each session, and the constructed graphs consist of only one type of user-item interaction. To address these limitations, we propose knowledge graph-based session recommendation with session-adaptive propagation. Specifically, we build a knowledge graph by connecting items with multi-typed edges to characterize various user-item interactions. Then, we adaptively aggregate items' neighbor information considering user intention within the learned session. Experimental results demonstrate that equipping our constructed knowledge graph and session-adaptive propagation enhances session recommendation backbones by 10%-20%. Moreover, we provide an industrial case study showing our proposed framework achieves 2% performance boost over an existing well-deployed model at The Home Depot e-platform.