Multi-domain Recommendation with Embedding Disentangling and Domain Alignment

TL;DR

This paper introduces EDDA, a multi-domain recommendation method that disentangles embeddings and aligns domains to improve knowledge transfer and recommendation accuracy across overlapping user/item spaces.

Contribution

The paper proposes EDDA, a novel MDR approach combining embedding disentangling at model and embedding levels with graph-based domain alignment, addressing knowledge disentanglement and transfer challenges.

Findings

EDDA outperforms 12 baselines on 3 real datasets.

Embedding disentangling improves domain-specific and general knowledge separation.

Domain alignment enhances knowledge transfer across domains.

Abstract

Multi-domain recommendation (MDR) aims to provide recommendations for different domains (e.g., types of products) with overlapping users/items and is common for platforms such as Amazon, Facebook, and LinkedIn that host multiple services. Existing MDR models face two challenges: First, it is difficult to disentangle knowledge that generalizes across domains (e.g., a user likes cheap items) and knowledge specific to a single domain (e.g., a user likes blue clothing but not blue cars). Second, they have limited ability to transfer knowledge across domains with small overlaps. We propose a new MDR method named EDDA with two key components, i.e., embedding disentangling recommender and domain alignment, to tackle the two challenges respectively. In particular, the embedding disentangling recommender separates both the model and embedding for the inter-domain part and the intra-domain part, while most existing MDR methods only focus on model-level disentangling. The domain alignment leverages random walks from graph processing to identify similar user/item pairs from different domains and encourages similar user/item pairs to have similar embeddings, enhancing knowledge transfer. We compare EDDA with 12 state-of-the-art baselines on 3 real datasets. The results show that EDDA consistently outperforms the baselines on all datasets and domains. All datasets and codes are available at https://github.com/Stevenn9981/EDDA.