CDC: Causal Domain Clustering for Multi-Domain Recommendation

2025/07/09 by Huishi Luo, Luo, Huishi, Yiqing Wu +7 · 1 citation
Computer Science · #Advanced Graph Neural Networks #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Recommender Systems and Techniques

paper · pdf · doi:10.48550/arxiv.2507.06877

openalex publication_date 2025/07/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Multi-domain recommendation leverages domain-general knowledge to improve recommendations across several domains. However, as platforms expand to dozens or hundreds of scenarios, training all domains in a unified model leads to performance degradation due to significant inter-domain differences. Existing domain grouping methods, based on business logic or data similarities, often fail to capture the true transfer relationships required for optimal grouping. To effectively cluster domains, we propose Causal Domain Clustering (CDC). CDC models domain transfer patterns within a large number of domains using two distinct effects: the Isolated Domain Affinity Matrix for modeling non-interactive domain transfers, and the Hybrid Domain Affinity Matrix for considering dynamic domain synergy or interference under joint training. To integrate these two transfer effects, we introduce causal discovery to calculate a cohesion-based coefficient that adaptively balances their contributions. A Co-Optimized Dynamic Clustering algorithm iteratively optimizes target domain clustering and source domain selection for training. CDC significantly enhances performance across over 50 domains on public datasets and in industrial settings, achieving a 4.9% increase in online eCPM. Code is available at https://github.com/Chrissie-Law/Causal-Domain-Clustering-for-Multi-Domain-Recommendation

Citations

• Deep Task-specific Bottom Representation Network for Multi-Task Recommendation
• PEPNet: Parameter and Embedding Personalized Network for Infusing with Personalized Prior Information
• AdaSparse: Learning Adaptively Sparse Structures for Multi-Domain Click-Through Rate Prediction
• Auto-Lambda: Disentangling Dynamic Task Relationships
• Efficiently Identifying Task Groupings for Multi-Task Learning
• A Distance Covariance-based Kernel for Nonlinear Causal Clustering in Heterogeneous Populations
• One Model to Serve All: Star Topology Adaptive Recommender for Multi-Domain CTR Prediction
• Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics
• Which Tasks Should Be Learned Together in Multi-task Learning?
• Entire Space Multi-Task Model: An Effective Approach for Estimating Post-Click Conversion Rate
• Deep & Cross Network for Ad Click Predictions
• DeepFM: A Factorization-Machine based Neural Network for CTR Prediction
• HyperNetworks
• Adam: A Method for Stochastic Optimization
• An introduction to ROC analysis

Cited by

• A Soft-partitioned Semi-supervised Collaborative Transfer Learning Approach for Multi-Domain Recommendation

Related

• Measure Domain's Gap: A Similar Domain Selection Principle for Multi-Domain Recommendation
• One for Dozens: Adaptive REcommendation for All Domains with Counterfactual Augmentation
• Causality Enhancement for Cross-Domain Recommendation
• Improving Cross-domain Recommendation through Probabilistic Cluster-level Latent Factor Model--Extended Version
• A Soft-partitioned Semi-supervised Collaborative Transfer Learning Approach for Multi-Domain Recommendation