# Negative Sampling for Contrastive Representation Learning: A Review

arXiv: https://arxiv.org/abs/2206.00212 · HTML: https://mlsanity.com/paper/2206.00212/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jun 2022.

## Built on by (most cited first, 23 of 23)

- [TimesURL: Self-supervised Contrastive Learning for Universal Time Series Representation Learning](https://mlsanity.com/paper/2312.15709/) (2023)
- [Boosting Masked ECG-Text Auto-Encoders as Discriminative Learners](https://mlsanity.com/paper/2410.02131/) (2024)
- [Negating Negatives: Alignment with Human Negative Samples via Distributional Dispreference Optimization](https://mlsanity.com/paper/2403.03419/) (2024)
- [Neighborhood-Enhanced Supervised Contrastive Learning for Collaborative Filtering](https://mlsanity.com/paper/2402.11523/) (2024)
- [ChatGPT-Like Large-Scale Foundation Models for Prognostics and Health Management: A Survey and Roadmaps](https://mlsanity.com/paper/2305.06472/) (2023)
- [Improving Contextualized Topic Models with Negative Sampling](https://mlsanity.com/paper/2303.14951/) (2023)
- [From Overfitting to Robustness: Quantity, Quality, and Variety Oriented Negative Sample Selection in Graph Contrastive Learning](https://mlsanity.com/paper/2406.15044/) (2024)
- [Taxonomy of the Retrieval System Framework: Pitfalls and Paradigms](https://mlsanity.com/paper/2601.20131/) (2026)
- [Bayesian Self-Supervised Contrastive Learning](https://mlsanity.com/paper/2301.11673/) (2023)
- [Revealing Multimodal Causality with Large Language Models](https://mlsanity.com/paper/2509.17784/) (2025)
- [Graph Your Own Prompt](https://mlsanity.com/paper/2509.23373/) (2025)
- [Contrastive Learning with Narrative Twins for Modeling Story Salience](https://mlsanity.com/paper/2601.07765/) (2026)
- [Topology-aware Debiased Self-supervised Graph Learning for Recommendation](https://mlsanity.com/paper/2310.15858/) (2023)
- [Paying Attention to Deflections: Mining Pragmatic Nuances for Whataboutism Detection in Online Discourse](https://mlsanity.com/paper/2402.09934/) (2024)
- [Stimulate the Potential of Robots via Competition](https://mlsanity.com/paper/2403.10487/) (2024)
- [Evaluating Multi-Hop Reasoning in RAG Systems: A Comparison of LLM-Based Retriever Evaluation Strategies](https://mlsanity.com/paper/2604.18234/) (2026)
- [An Energy-based Model for Word-level AutoCompletion in Computer-aided Translation](https://mlsanity.com/paper/2407.20083/) (2024)
- [Evaluating Negative Sampling Approaches for Neural Topic Models](https://mlsanity.com/paper/2503.18167/) (2025)
- [Advancing Wildfire Risk Prediction via Morphology-Aware Curriculum Contrastive Learning](https://mlsanity.com/paper/2507.21147/) (2025)
- [Causal Negative Sampling via Diffusion Model for Out-of-Distribution Recommendation](https://mlsanity.com/paper/2508.07243/) (2025)
- [Osmotic Learning: A Self-Supervised Paradigm for Decentralized Contextual Data Representation](https://mlsanity.com/paper/2512.23096/) (2025)
- [LEMON: a foundation model for nuclear morphology in Computational Pathology](https://mlsanity.com/paper/2603.25802/) (2026)
- [MiqraBERT: Regression-Based Sentence-BERT Finetuning for Biblical Hebrew Parallel Detection](https://mlsanity.com/paper/2606.19638/) (2026)

## Abstract (arXiv)

The learn-to-compare paradigm of contrastive representation learning (CRL), which compares positive samples with negative ones for representation learning, has achieved great success in a wide range of domains, including natural language processing, computer vision, information retrieval and graph learning. While many research works focus on data augmentations, nonlinear transformations or other certain parts of CRL, the importance of negative sample selection is usually overlooked in literature. In this paper, we provide a systematic review of negative sampling (NS) techniques and discuss how they contribute to the success of CRL. As the core part of this paper, we summarize the existing NS methods into four categories with pros and cons in each genre, and further conclude with several open research questions as future directions. By generalizing and aligning the fundamental NS ideas across multiple domains, we hope this survey can accelerate cross-domain knowledge sharing and motivate future researches for better CRL.