# Alignment and Uniformity

> [!NOTE]
>
> **In one minute**
>
> A good representation keeps similar instances close together and separates different ones. Wang and Isola (2020) call these two properties alignment and uniformity and describe both on a hypersphere.

A good representation should be able to

- separate different instances, and
- cluster similar instances.

Wang et al proposed two concepts that matches the above two ideas, alignment and uniformity, on a hypersphere[^/concepts/alignment-and-uniformity/#Wang2005].

![From Wang et al](<https://dl.leima.is/concepts/assets/alignment-and-uniformity/wang2005-alignment-uniformity.png>)

> From Wang et al[^/concepts/alignment-and-uniformity/#Wang2005].

---

**Related:** [Contrastive Predictive Coding](<https://dl.leima.is/self-supervised/contrastive/contrastive-predictive-coding/index.md>) · [Deep Infomax](<https://dl.leima.is/self-supervised/contrastive/deep-infomax/index.md>)

[^/concepts/alignment-and-uniformity/#Wang2005]: Wang T, Isola P. Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere. arXiv \[cs.LG\]. 2020. Available: [http://arxiv.org/abs/2005.10242](<http://arxiv.org/abs/2005.10242 >)
