# Difficult Examples Hurt Unsupervised Contrastive Learning: A Theoretical Perspective

arXiv: https://arxiv.org/abs/2501.01317 · HTML: https://mlsanity.com/paper/2501.01317/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 50 references that are in the map.
- First posted on arXiv 2 Jan 2025.

## Builds on (most cited first, 30 of 42)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Contrastive Learning with Hard Negative Samples](https://mlsanity.com/paper/2010.04592/) (2020)
- [Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View](https://mlsanity.com/paper/1909.03211/) (2019)
- [A Theoretical Analysis of Contrastive Unsupervised Representation Learning](https://mlsanity.com/paper/1902.09229/) (2019)
- [Hard Negative Mixing for Contrastive Learning](https://mlsanity.com/paper/2010.01028/) (2020)
- [Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss](https://mlsanity.com/paper/2106.04156/) (2021)
- [Contrastive Learning Inverts the Data Generating Process](https://mlsanity.com/paper/2102.08850/) (2021)
- [Exploring Deep Neural Networks via Layer-Peeled Model: Minority Collapse in Imbalanced Training](https://mlsanity.com/paper/2101.12699/) (2021)
- [Contrastive and Non-Contrastive Self-Supervised Learning Recover Global and Local Spectral Embedding Methods](https://mlsanity.com/paper/2205.11508/) (2022)
- [Gradient Harmonized Single-stage Detector](https://mlsanity.com/paper/1811.05181/) (2018)
- [Chaos is a Ladder: A New Theoretical Understanding of Contrastive Learning via Augmentation Overlap](https://mlsanity.com/paper/2203.13457/) (2022)
- [Towards the Generalization of Contrastive Self-Supervised Learning](https://mlsanity.com/paper/2111.00743/) (2021)
- [Distributional Robustness Loss for Long-tail Learning](https://mlsanity.com/paper/2104.03066/) (2021)
- [Sequence-to-Sequence Contrastive Learning for Text Recognition](https://mlsanity.com/paper/2012.10873/) (2020)
- [Connect, Not Collapse: Explaining Contrastive Learning for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2204.00570/) (2022)
- [Investigating the Role of Negatives in Contrastive Representation Learning](https://mlsanity.com/paper/2106.09943/) (2021)
- [Understanding Negative Samples in Instance Discriminative Self-supervised Representation Learning](https://mlsanity.com/paper/2102.06866/) (2021)
- [Temperature Schedules for Self-Supervised Contrastive Methods on Long-Tail Data](https://mlsanity.com/paper/2303.13664/) (2023)
- [Towards a Unified Theoretical Understanding of Non-contrastive Learning via Rank Differential Mechanism](https://mlsanity.com/paper/2303.02387/) (2023)
- [Contrastive Learning Can Find An Optimal Basis For Approximately View-Invariant Functions](https://mlsanity.com/paper/2210.01883/) (2022)
- [Residual Relaxation for Multi-view Representation Learning](https://mlsanity.com/paper/2110.15348/) (2021)
- [On the Generalization of Multi-modal Contrastive Learning](https://mlsanity.com/paper/2306.04272/) (2023)

## Built on by (most cited first, 2 of 2)

- [A Generalization Theory for JEPA-Based World Models](https://mlsanity.com/paper/2606.27014/) (2026)
- [A Theoretical Framework for Masked Pretraining (MPT)](https://mlsanity.com/paper/2609.06460/) (2026)

## Abstract (arXiv)

Unsupervised contrastive learning has shown significant performance improvements in recent years, often approaching or even rivaling supervised learning in various tasks. However, its learning mechanism is fundamentally different from supervised learning. Previous works have shown that difficult examples (well-recognized in supervised learning as examples around the decision boundary), which are essential in supervised learning, contribute minimally in unsupervised settings. In this paper, perhaps surprisingly, we find that the direct removal of difficult examples, although reduces the sample size, can boost the downstream classification performance of contrastive learning. To uncover the reasons behind this, we develop a theoretical framework modeling the similarity between different pairs of samples. Guided by this framework, we conduct a thorough theoretical analysis revealing that the presence of difficult examples negatively affects the generalization of contrastive learning. Furthermore, we demonstrate that the removal of these examples, and techniques such as margin tuning and temperature scaling can enhance its generalization bounds, thereby improving performance. Empirically, we propose a simple and efficient mechanism for selecting difficult examples and validate the effectiveness of the aforementioned methods, which substantiates the reliability of our proposed theoretical framework.