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

TL;DR

This paper introduces MI-DPG, a novel multi-scenario CVR prediction model that efficiently generates scenario-specific parameters using mutual information regularization to improve diversity and performance across different recommendation scenarios.

Contribution

The paper proposes a decomposable parameter generation network with mutual information regularization for multi-scenario recommendation, enhancing diversity and efficiency.

Findings

Outperforms previous multi-scenario recommendation models on real-world datasets.

Effectively models scenario-specific diversity with mutual information regularization.

Achieves higher prediction accuracy with lower parameter cost.

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.