# Simplify and Robustify Negative Sampling for Implicit Collaborative Filtering

arXiv: https://arxiv.org/abs/2009.03376 · HTML: https://mlsanity.com/paper/2009.03376/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Sep 2020.

## Built on by (most cited first, 30 of 34)

- [Unsupervised Path Representation Learning with Curriculum Negative Sampling](https://mlsanity.com/paper/2106.09373/) (2021)
- [Double Correction Framework for Denoising Recommendation](https://mlsanity.com/paper/2405.11272/) (2024)
- [On the Theories Behind Hard Negative Sampling for Recommendation](https://mlsanity.com/paper/2302.03472/) (2023)
- [Does Negative Sampling Matter? A Review with Insights into its Theory and Applications](https://mlsanity.com/paper/2402.17238/) (2024)
- [Scalable Cross-Entropy Loss for Sequential Recommendations with Large Item Catalogs](https://mlsanity.com/paper/2409.18721/) (2024)
- [Distillation from Heterogeneous Models for Top-K Recommendation](https://mlsanity.com/paper/2303.01130/) (2023)
- [End-to-end Training for Recommendation with Language-based User Profiles](https://mlsanity.com/paper/2410.18870/) (2024)
- [Diffusion-based Negative Sampling on Graphs for Link Prediction](https://mlsanity.com/paper/2403.17259/) (2024)
- [RECE: Reduced Cross-Entropy Loss for Large-Catalogue Sequential Recommenders](https://mlsanity.com/paper/2408.02354/) (2024)
- [Toward a Better Understanding of Loss Functions for Collaborative Filtering](https://mlsanity.com/paper/2308.06091/) (2023)
- [Learning Explicit User Interest Boundary for Recommendation](https://mlsanity.com/paper/2111.11026/) (2021)
- [Consensus Learning from Heterogeneous Objectives for One-Class Collaborative Filtering](https://mlsanity.com/paper/2202.13140/) (2022)
- [Neighborhood-based Hard Negative Mining for Sequential Recommendation](https://mlsanity.com/paper/2306.10047/) (2023)
- [Revisiting Recommendation Loss Functions through Contrastive Learning (Technical Report)](https://mlsanity.com/paper/2312.08520/) (2023)
- [Beyond Single Labels: Improving Conversational Recommendation through LLM-Powered Data Augmentation](https://mlsanity.com/paper/2508.05657/) (2025)
- [SCONE: A Novel Stochastic Sampling to Generate Contrastive Views and Hard Negative Samples for Recommendation](https://mlsanity.com/paper/2405.00287/) (2024)
- [Large Language Model Enhanced Hard Sample Identification for Denoising Recommendation](https://mlsanity.com/paper/2409.10343/) (2024)
- [Dimension Independent Mixup for Hard Negative Sample in Collaborative Filtering](https://mlsanity.com/paper/2306.15905/) (2023)
- [Knowledge Distillation Approaches for Accurate and Efficient Recommender System](https://mlsanity.com/paper/2407.13952/) (2024)
- [BehaveGPT: A Foundation Model for Large-scale User Behavior Modeling](https://mlsanity.com/paper/2505.17631/) (2025)
- [Bayesian Negative Sampling for Recommendation](https://mlsanity.com/paper/2204.06520/) (2022)
- [Graph-Based Model-Agnostic Data Subsampling for Recommendation Systems](https://mlsanity.com/paper/2305.16391/) (2023)
- [Representer Point Selection for Explaining Regularized High-dimensional Models](https://mlsanity.com/paper/2305.20002/) (2023)
- [Curriculum Negative Mining For Temporal Networks](https://mlsanity.com/paper/2407.17070/) (2024)
- [Scalable Personalised Item Ranking through Parametric Density Estimation](https://mlsanity.com/paper/2105.04769/) (2021)
- [One-class Recommendation Systems with the Hinge Pairwise Distance Loss and Orthogonal Representations](https://mlsanity.com/paper/2208.14594/) (2022)
- [DPR: An Algorithm Mitigate Bias Accumulation in Recommendation feedback loops](https://mlsanity.com/paper/2311.05864/) (2023)
- [(Debiased) Contrastive Learning Loss for Recommendation (Technical Report)](https://mlsanity.com/paper/2312.08517/) (2023)
- [Exploiting Preferences in Loss Functions for Sequential Recommendation via Weak Transitivity](https://mlsanity.com/paper/2408.00326/) (2024)
- [MixDec Sampling: A Soft Link-based Sampling Method of Graph Neural Network for Recommendation](https://mlsanity.com/paper/2502.08161/) (2025)

## Abstract (arXiv)

Negative sampling approaches are prevalent in implicit collaborative filtering for obtaining negative labels from massive unlabeled data. As two major concerns in negative sampling, efficiency and effectiveness are still not fully achieved by recent works that use complicate structures and overlook risk of false negative instances. In this paper, we first provide a novel understanding of negative instances by empirically observing that only a few instances are potentially important for model learning, and false negatives tend to have stable predictions over many training iterations. Above findings motivate us to simplify the model by sampling from designed memory that only stores a few important candidates and, more importantly, tackle the untouched false negative problem by favouring high-variance samples stored in memory, which achieves efficient sampling of true negatives with high-quality. Empirical results on two synthetic datasets and three real-world datasets demonstrate both robustness and superiorities of our negative sampling method.