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

Source: [MI-DPG: Decomposable Parameter Generation Network Based on Mutual Information for Multi-Scenario Recommendation](<https://www.sota2.com/research/paper/69c21abe0636e5bf4afc4b95>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-25T05:00:11.826Z

Authors: Wenzhuo Cheng, Ke Ding, Xin Dong, Yong He, Liang Zhang, Linjian Mo

Published: 2026-03-22T13:07:14.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [CVR Prediction on Amazon](<https://www.sota2.com/research/sota/cvr-prediction-on-amazon.md>): CVR prediction; AMAZON; AUC: 67.45.

- [CVR Prediction on IAAC](<https://www.sota2.com/research/sota/cvr-prediction-on-iaac.md>): CVR prediction; IAAC; AUC: 0.6504.

- [CVR Prediction on Advertising](<https://www.sota2.com/research/sota/cvr-prediction-on-advertising.md>): CVR prediction; Advertising; AUC: 75.8.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.21209>)

[PDF](<https://arxiv.org/pdf/2603.21209.pdf>)
