MI-DPG: Decomposable Parameter Generation Network Based on Mutual Information for Multi-Scenario Recommendation

2026-03-22

AI Summary

This work addresses the trade-off between cross-scenario conversion rate (CVR) prediction performance and parameter efficiency in multi-scenario recommendation. To this end, the authors propose the MI-DPG model, which decouples backbone network parameters into scenario-shared and scenario-specific components via low-rank decomposition and employs a lightweight auxiliary network to generate dynamic weight matrices for parameter customization. Furthermore, the model innovatively incorporates a mutual information maximization regularizer to enhance the diversity of parameter distributions across scenarios. Extensive experiments on three real-world datasets demonstrate that MI-DPG significantly outperforms existing methods, achieving superior CVR prediction accuracy while maintaining low parameter overhead.

Technology Category

• Machine Learning: Mixture of Experts (MoE)
• Computer Vision: Learning & Optimization for CV
• Search and Optimization: Learning to Search

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Conversion rate (CVR) prediction models play a vital role in recommendation and advertising systems. Recent research on multi-scenario recommendation shows that learning a unified model to serve multiple scenarios is effective for improving overall performance. However, it remains challenging to improve model prediction performance across scenarios at low model parameter cost, and current solutions are hard to robustly model multi-scenario diversity. In this paper, we propose MI-DPG for the multi-scenario CVR prediction, which learns scenario-conditioned dynamic model parameters for each scenario in a more efficient and effective manner. Specifically, we introduce an auxiliary network to generate scenario-conditioned dynamic weighting matrices, which are obtained by combining decomposed scenario-specific and scenario-shared low-rank matrices with parameter efficiency. For each scene, weighting the backbone model parameters by the weighting matrix helps to specialize the model parameters for different scenarios. It can not only modulate the complete parameter space of the backbone model but also improve the model effectiveness. Furthermore, we design a mutual information regularization to enhance the diversity of model parameters across different scenarios by maximizing the mutual information between the scenario-aware input and the scene-conditioned dynamic weighting matrix. Experiments from three real-world datasets show that MI-DPG significantly outperforms previous multi-scenario recommendation models.

Problem

• multi-scenario recommendation
• CVR prediction
• parameter efficiency
• model diversity
• scenario heterogeneity

Innovation

• Decomposable Parameter Generation
• Mutual Information Regularization
• Multi-Scenario Recommendation
• Dynamic Weighting Matrix
• Low-Rank Decomposition