# Improving Accuracy and Diversity in Matching of Recommendation with Diversified Preference Network

arXiv: https://arxiv.org/abs/2102.03787 · HTML: https://mlsanity.com/paper/2102.03787/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Feb 2021.

## Built on by (most cited first, 8 of 8)

- [Improved Diversity-Promoting Collaborative Metric Learning for Recommendation](https://mlsanity.com/paper/2409.01012/) (2024)
- [RADio -- Rank-Aware Divergence Metrics to Measure Normative Diversity in News Recommendations](https://mlsanity.com/paper/2209.13520/) (2022)
- [Heterophily-Aware Fair Recommendation using Graph Convolutional Networks](https://mlsanity.com/paper/2402.03365/) (2024)
- [Ada-Retrieval: An Adaptive Multi-Round Retrieval Paradigm for Sequential Recommendations](https://mlsanity.com/paper/2401.06633/) (2024)
- [Graph Exploration Matters: Improving both individual-level and system-level diversity in WeChat Feed Recommender](https://mlsanity.com/paper/2306.00009/) (2023)
- [Empirical and Experimental Perspectives on Big Data in Recommendation Systems: A Comprehensive Survey](https://mlsanity.com/paper/2402.03368/) (2024)
- [Separated Contrastive Learning for Matching in Cross-domain Recommendation with Curriculum Scheduling](https://mlsanity.com/paper/2502.16239/) (2025)
- [Towards Multi-Aspect Diversification of News Recommendations Using Neuro-Symbolic AI for Individual and Societal Benefit](https://mlsanity.com/paper/2509.02220/) (2025)

## Abstract (arXiv)

Recently, real-world recommendation systems need to deal with millions of candidates. It is extremely challenging to conduct sophisticated end-to-end algorithms on the entire corpus due to the tremendous computation costs. Therefore, conventional recommendation systems usually contain two modules. The matching module focuses on the coverage, which aims to efficiently retrieve hundreds of items from large corpora, while the ranking module generates specific ranks for these items. Recommendation diversity is an essential factor that impacts user experience. Most efforts have explored recommendation diversity in ranking, while the matching module should take more responsibility for diversity. In this paper, we propose a novel Heterogeneous graph neural network framework for diversified recommendation (GraphDR) in matching to improve both recommendation accuracy and diversity. Specifically, GraphDR builds a huge heterogeneous preference network to record different types of user preferences, and conduct a field-level heterogeneous graph attention network for node aggregation. We also innovatively conduct a neighbor-similarity based loss to balance both recommendation accuracy and diversity for the diversified matching task. In experiments, we conduct extensive online and offline evaluations on a real-world recommendation system with various accuracy and diversity metrics and achieve significant improvements. We also conduct model analyses and case study for a better understanding of our model. Moreover, GraphDR has been deployed on a well-known recommendation system, which affects millions of users. The source code will be released.