HAMUR: Hyper Adapter for Multi-Domain Recommendation

Abstract

Multi-Domain Recommendation (MDR) has gained significant attention in recent years, which leverages data from multiple domains to enhance their performance concurrently.However, current MDR models are confronted with two limitations. Firstly, the majority of these models adopt an approach that explicitly shares parameters between domains, leading to mutual interference among them. Secondly, due to the distribution differences among domains, the utilization of static parameters in existing methods limits their flexibility to adapt to diverse domains. To address these challenges, we propose a novel model Hyper Adapter for Multi-Domain Recommendation (HAMUR). Specifically, HAMUR consists of two components: (1). Domain-specific adapter, designed as a pluggable module that can be seamlessly integrated into various existing multi-domain backbone models, and (2). Domain-shared hyper-network, which implicitly captures shared information among domains and dynamically generates the parameters for the adapter. We conduct extensive experiments on two public datasets using various backbone networks. The experimental results validate the effectiveness and scalability of the proposed model.

Accepted by CIKM'2023

References in corpus (8)

• HyperNetworks
• SAR-Net: A Scenario-Aware Ranking Network for Personalized Fair Recommendation in Hundreds of Travel Scenarios
• AutoMLP: Automated MLP for Sequential Recommendations
• DDTCDR: Deep Dual Transfer Cross Domain Recommendation
• APG: Adaptive Parameter Generation Network for Click-Through Rate Prediction
• Leaving No One Behind: A Multi-Scenario Multi-Task Meta Learning Approach for Advertiser Modeling
• Hypernetworks in Meta-Reinforcement Learning
• AdaptDHM: Adaptive Distribution Hierarchical Model for Multi-Domain CTR Prediction

Cited by in corpus (7)

• M3oE: Multi-Domain Multi-Task Mixture-of Experts Recommendation Framework
• ABXI: Invariant Interest Adaptation for Task-Guided Cross-Domain Sequential Recommendation
• Multi-task Offline Reinforcement Learning for Online Advertising in Recommender Systems
• PERSCEN: Learning Personalized Interaction Pattern and Scenario Preference for Multi-Scenario Matching
• SPARK: Adaptive Low-Rank Knowledge Graph Modeling in Hybrid Geometric Spaces for Recommendation
• Empowering Denoising Sequential Recommendation with Large Language Model Embeddings
• Prompt Tuning as User Inherent Profile Inference Machine