Knowledge-aware Neural Networks with Personalized Feature Referencing for Cold-start Recommendation

TL;DR

This paper introduces KPER, a knowledge-aware neural network that leverages knowledge graphs as semantic bridges to improve cold-start recommendation by referencing relevant features from similar users or items.

Contribution

KPER employs a personalized feature referencing mechanism using knowledge graphs, enhancing cold-start recommendation performance without sacrificing overall accuracy.

Findings

KPER outperforms existing methods in cold-start scenarios across four datasets.

KPER achieves 0.81%-16.08% improvement in Top-10 recommendation.

KPER maintains strong performance in general scenarios.

Abstract

Incorporating knowledge graphs (KGs) as side information in recommendation has recently attracted considerable attention. Despite the success in general recommendation scenarios, prior methods may fall short of performance satisfaction for the cold-start problem in which users are associated with very limited interactive information. Since the conventional methods rely on exploring the interaction topology, they may however fail to capture sufficient information in cold-start scenarios. To mitigate the problem, we propose a novel Knowledge-aware Neural Networks with Personalized Feature Referencing Mechanism, namely KPER. Different from most prior methods which simply enrich the targets' semantics from KGs, e.g., product attributes, KPER utilizes the KGs as a "semantic bridge" to extract feature references for cold-start users or items. Specifically, given cold-start targets, KPER first probes semantically relevant but not necessarily structurally close users or items as adaptive seeds for referencing features. Then a Gated Information Aggregation module is introduced to learn the combinatorial latent features for cold-start users and items. Our extensive experiments over four real-world datasets show that, KPER consistently outperforms all competing methods in cold-start scenarios, whilst maintaining superiority in general scenarios without compromising overall performance, e.g., by achieving 0.81%-16.08% and 1.01%-14.49% performance improvement across all datasets in Top-10 recommendation.