One for Dozens: Adaptive REcommendation for All Domains with Counterfactual Augmentation

TL;DR

This paper introduces AREAD, a hierarchical, adaptive recommendation model that effectively handles dozens of domains, especially benefiting data-sparse minor domains through counterfactual data augmentation and dynamic expert network selection.

Contribution

The paper proposes a novel hierarchical expert network with adaptive domain knowledge transfer and counterfactual augmentation to improve multi-domain recommendation at scale.

Findings

Effective in over twenty domains, especially minor ones.

Outperforms traditional methods in data-sparse domains.

Demonstrates scalability to hundreds of domains.

Abstract

Multi-domain recommendation (MDR) aims to enhance recommendation performance across various domains. However, real-world recommender systems in online platforms often need to handle dozens or even hundreds of domains, far exceeding the capabilities of traditional MDR algorithms, which typically focus on fewer than five domains. Key challenges include a substantial increase in parameter count, high maintenance costs, and intricate knowledge transfer patterns across domains. Furthermore, minor domains often suffer from data sparsity, leading to inadequate training in classical methods. To address these issues, we propose Adaptive REcommendation for All Domains with counterfactual augmentation (AREAD). AREAD employs a hierarchical structure with a limited number of expert networks at several layers, to effectively capture domain knowledge at different granularities. To adaptively capture the knowledge transfer pattern across domains, we generate and iteratively prune a hierarchical expert network selection mask for each domain during training. Additionally, counterfactual assumptions are used to augment data in minor domains, supporting their iterative mask pruning. Our experiments on two public datasets, each encompassing over twenty domains, demonstrate AREAD's effectiveness, especially in data-sparse domains. Source code is available at https://github.com/Chrissie-Law/AREAD-Multi-Domain-Recommendation.