# Graph-Based Model-Agnostic Data Subsampling for Recommendation Systems

arXiv: https://arxiv.org/abs/2305.16391 · HTML: https://mlsanity.com/paper/2305.16391/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 43 references that are in the map.
- First posted on arXiv 25 May 2023.

## Builds on (most cited first, 22 of 22)

- [Graph Convolutional Neural Networks for Web-Scale Recommender Systems](https://mlsanity.com/paper/1806.01973/) (2018)
- [Wide & Deep Learning for Recommender Systems](https://mlsanity.com/paper/1606.07792/) (2016)
- [DeepFM: A Factorization-Machine based Neural Network for CTR Prediction](https://mlsanity.com/paper/1703.04247/) (2017)
- [Contrastive Learning with Hard Negative Samples](https://mlsanity.com/paper/2010.04592/) (2020)
- [Measuring Calibration in Deep Learning](https://mlsanity.com/paper/1904.01685/) (2019)
- [Combining Label Propagation and Simple Models Out-performs Graph Neural Networks](https://mlsanity.com/paper/2010.13993/) (2020)
- [Neural Factorization Machines for Sparse Predictive Analytics](https://mlsanity.com/paper/1708.05027/) (2017)
- [Embedding-based Retrieval in Facebook Search](https://mlsanity.com/paper/2006.11632/) (2020)
- [KuaiRec: A Fully-observed Dataset and Insights for Evaluating Recommender Systems](https://mlsanity.com/paper/2202.10842/) (2022)
- [IRGAN: A Minimax Game for Unifying Generative and Discriminative Information Retrieval Models](https://mlsanity.com/paper/1705.10513/) (2017)
- [On Sampling Strategies for Neural Network-based Collaborative Filtering](https://mlsanity.com/paper/1706.07881/) (2017)
- [Graph Coarsening with Neural Networks](https://mlsanity.com/paper/2102.01350/) (2021)
- [AutoFIS: Automatic Feature Interaction Selection in Factorization Models for Click-Through Rate Prediction](https://mlsanity.com/paper/2003.11235/) (2020)
- [Simplify and Robustify Negative Sampling for Implicit Collaborative Filtering](https://mlsanity.com/paper/2009.03376/) (2020)
- [Continuous Integration, Delivery and Deployment: A Systematic Review on Approaches, Tools, Challenges and Practices](https://mlsanity.com/paper/1703.07019/) (2017)
- [Local case-control sampling: Efficient subsampling in imbalanced data sets](https://mlsanity.com/paper/1306.3706/) (2013)
- [Optimal Sub-sampling with Influence Functions](https://mlsanity.com/paper/1709.01716/) (2017)
- [Structure-Preserving Sparsification Methods for Social Networks](https://mlsanity.com/paper/1601.00286/) (2016)
- [Logistic Regression for Massive Data with Rare Events](https://mlsanity.com/paper/2006.00683/) (2020)
- [Local Uncertainty Sampling for Large-Scale Multi-Class Logistic Regression](https://mlsanity.com/paper/1604.08098/) (2016)
- [Nonuniform Negative Sampling and Log Odds Correction with Rare Events Data](https://mlsanity.com/paper/2110.13048/) (2021)
- [Surprise sampling: improving and extending the local case-control sampling](https://mlsanity.com/paper/2007.02633/) (2020)

## Built on by (most cited first, 1 of 1)

- [Simplifying Graph Convolutional Networks with Redundancy-Free Neighbors](https://mlsanity.com/paper/2504.13426/) (2025)

## Abstract (arXiv)

Data subsampling is widely used to speed up the training of large-scale recommendation systems. Most subsampling methods are model-based and often require a pre-trained pilot model to measure data importance via e.g. sample hardness. However, when the pilot model is misspecified, model-based subsampling methods deteriorate. Since model misspecification is persistent in real recommendation systems, we instead propose model-agnostic data subsampling methods by only exploring input data structure represented by graphs. Specifically, we study the topology of the user-item graph to estimate the importance of each user-item interaction (an edge in the user-item graph) via graph conductance, followed by a propagation step on the network to smooth out the estimated importance value. Since our proposed method is model-agnostic, we can marry the merits of both model-agnostic and model-based subsampling methods. Empirically, we show that combing the two consistently improves over any single method on the used datasets. Experimental results on KuaiRec and MIND datasets demonstrate that our proposed methods achieve superior results compared to baseline approaches.