MeKB-Rec: Personal Knowledge Graph Learning for Cross-Domain Recommendation

TL;DR

This paper introduces MeKB-Rec, a novel cross-domain recommendation approach using personal knowledge graphs and pretrained language models to enable zero-shot recommendations for new users, significantly outperforming previous methods.

Contribution

It proposes a domain-invariant user interest representation via personal knowledge graphs and a semantic mapping approach that enables zero-shot recommendations across domains.

Findings

Achieves 24-91% improvement in HR@10 and NDCG@10 metrics over previous methods.

Enables zero-shot recommendations with 105% improvement for new users.

Deployed in WeiXin, serving hundreds of millions of users with significant online metric gains.

Abstract

It is a long-standing challenge in modern recommender systems to effectively make recommendations for new users, namely the cold-start problem. Cross-Domain Recommendation (CDR) has been proposed to address this challenge, but current ways to represent users' interests across systems are still severely limited. We introduce Personal Knowledge Graph (PKG) as a domain-invariant interest representation, and propose a novel CDR paradigm named MeKB-Rec. We first link users and entities in a knowledge base to construct a PKG of users' interests, named MeKB. Then we learn a semantic representation of MeKB for the cross-domain recommendation. To efficiently utilize limited training data in CDR, MeKB-Rec employs Pretrained Language Models to inject world knowledge into understanding users' interests. Beyond most existing systems, our approach builds a semantic mapping across domains which breaks the requirement for in-domain user behaviors, enabling zero-shot recommendations for new users in a low-resource domain. We experiment MeKB-Rec on well-established public CDR datasets, and demonstrate that the new formulation % is more powerful than previous approaches, achieves a new state-of-the-art that significantly improves HR@10 and NDCG@10 metrics over best previous approaches by 24\%--91\%, with a 105\% improvement for HR@10 of zero-shot users with no behavior in the target domain. We deploy MeKB-Rec in WeiXin recommendation scenarios and achieve significant gains in core online metrics. MeKB-Rec is now serving hundreds of millions of users in real-world products.