# Whitening-based Contrastive Learning of Sentence Embeddings

arXiv: https://arxiv.org/abs/2305.17746 · HTML: https://mlsanity.com/paper/2305.17746/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 54 references that are in the map.
- First posted on arXiv 28 May 2023.

## Builds on (most cited first, 29 of 29)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere](https://mlsanity.com/paper/2005.10242/) (2020)
- [SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation](https://mlsanity.com/paper/1708.00055/) (2017)
- [How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings](https://mlsanity.com/paper/1909.00512/) (2019)
- [Distributed Representations of Sentences and Documents](https://mlsanity.com/paper/1405.4053/) (2014)
- [Skip-Thought Vectors](https://mlsanity.com/paper/1506.06726/) (2015)
- [SentEval: An Evaluation Toolkit for Universal Sentence Representations](https://mlsanity.com/paper/1803.05449/) (2018)
- [Whitening for Self-Supervised Representation Learning](https://mlsanity.com/paper/2007.06346/) (2020)
- [ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer](https://mlsanity.com/paper/2105.11741/) (2021)
- [Whitening Sentence Representations for Better Semantics and Faster Retrieval](https://mlsanity.com/paper/2103.15316/) (2021)
- [An efficient framework for learning sentence representations](https://mlsanity.com/paper/1803.02893/) (2018)
- [On Feature Decorrelation in Self-Supervised Learning](https://mlsanity.com/paper/2105.00470/) (2021)
- [Self-Guided Contrastive Learning for BERT Sentence Representations](https://mlsanity.com/paper/2106.07345/) (2021)
- [Learning Distributed Representations of Sentences from Unlabelled Data](https://mlsanity.com/paper/1602.03483/) (2016)
- [An Unsupervised Sentence Embedding Method by Mutual Information Maximization](https://mlsanity.com/paper/2009.12061/) (2020)
- [Decorrelated Batch Normalization](https://mlsanity.com/paper/1804.08450/) (2018)
- [ESimCSE: Enhanced Sample Building Method for Contrastive Learning of Unsupervised Sentence Embedding](https://mlsanity.com/paper/2109.04380/) (2021)
- [Debiased Contrastive Learning of Unsupervised Sentence Representations](https://mlsanity.com/paper/2205.00656/) (2022)
- [CLINE: Contrastive Learning with Semantic Negative Examples for Natural Language Understanding](https://mlsanity.com/paper/2107.00440/) (2021)
- [Less is more: zero-shot learning from online textual documents with noise suppression](https://mlsanity.com/paper/1604.01146/) (2016)
- [Pairwise Supervised Contrastive Learning of Sentence Representations](https://mlsanity.com/paper/2109.05424/) (2021)
- [Virtual Augmentation Supported Contrastive Learning of Sentence Representations](https://mlsanity.com/paper/2110.08552/) (2021)

## Built on by (most cited first, 21 of 21)

- [AnglE-optimized Text Embeddings](https://mlsanity.com/paper/2309.12871/) (2023)
- [FonTS: Text Rendering with Typography and Style Controls](https://mlsanity.com/paper/2412.00136/) (2024)
- [BeLLM: Backward Dependency Enhanced Large Language Model for Sentence Embeddings](https://mlsanity.com/paper/2311.05296/) (2023)
- [PersonalVideo: High ID-Fidelity Video Customization without Dynamic and Semantic Degradation](https://mlsanity.com/paper/2411.17048/) (2024)
- [PlanGen: Towards Unified Layout Planning and Image Generation in Auto-Regressive Vision Language Models](https://mlsanity.com/paper/2503.10127/) (2025)
- [VividDreamer: Invariant Score Distillation For Hyper-Realistic Text-to-3D Generation](https://mlsanity.com/paper/2407.09822/) (2024)
- [InfiniDreamer: Arbitrarily Long Human Motion Generation via Segment Score Distillation](https://mlsanity.com/paper/2411.18303/) (2024)
- [MinD-3D: Reconstruct High-quality 3D objects in Human Brain](https://mlsanity.com/paper/2312.07485/) (2023)
- [Redundancy, Isotropy, and Intrinsic Dimensionality of Prompt-based Text Embeddings](https://mlsanity.com/paper/2506.01435/) (2025)
- [Position: Text Embeddings Should Capture Implicit Semantics, Not Just Surface Meaning](https://mlsanity.com/paper/2506.08354/) (2025)
- [2D Matryoshka Sentence Embeddings](https://mlsanity.com/paper/2402.14776/) (2024)
- [SemCoT: Accelerating Chain-of-Thought Reasoning through Semantically-Aligned Implicit Tokens](https://mlsanity.com/paper/2510.24940/) (2025)
- [Don't Reinvent the Wheel: Efficient Instruction-Following Text Embedding based on Guided Space Transformation](https://mlsanity.com/paper/2505.24754/) (2025)
- [From Trial to Triumph: Advancing Long Video Understanding via Visual Context Sample Scaling and Self-reward Alignment](https://mlsanity.com/paper/2503.20472/) (2025)
- [DALR: Dual-level Alignment Learning for Multimodal Sentence Representation Learning](https://mlsanity.com/paper/2506.21096/) (2025)
- [Characterizing Human Semantic Navigation in Concept Production as Trajectories in Embedding Space](https://mlsanity.com/paper/2602.05971/) (2026)
- [Injecting Wiktionary to improve token-level contextual representations using contrastive learning](https://mlsanity.com/paper/2402.07817/) (2024)
- [Whitening Not Recommended for Classification Tasks in LLMs](https://mlsanity.com/paper/2407.12886/) (2024)
- [LDIR: Low-Dimensional Dense and Interpretable Text Embeddings with Relative Representations](https://mlsanity.com/paper/2505.10354/) (2025)
- [reCSE: Portable Reshaping Features for Sentence Embedding in Self-supervised Contrastive Learning](https://mlsanity.com/paper/2408.04975/) (2024)
- [Keep Calm and Avoid Harmful Content: Concept Alignment and Latent Manipulation Towards Safer Answers](https://mlsanity.com/paper/2510.12672/) (2025)

## Abstract (arXiv)

This paper presents a whitening-based contrastive learning method for sentence embedding learning (WhitenedCSE), which combines contrastive learning with a novel shuffled group whitening. Generally, contrastive learning pulls distortions of a single sample (i.e., positive samples) close and push negative samples far away, correspondingly facilitating the alignment and uniformity in the feature space. A popular alternative to the "pushing'' operation is whitening the feature space, which scatters all the samples for uniformity. Since the whitening and the contrastive learning have large redundancy w.r.t. the uniformity, they are usually used separately and do not easily work together. For the first time, this paper integrates whitening into the contrastive learning scheme and facilitates two benefits. 1) Better uniformity. We find that these two approaches are not totally redundant but actually have some complementarity due to different uniformity mechanism. 2) Better alignment. We randomly divide the feature into multiple groups along the channel axis and perform whitening independently within each group. By shuffling the group division, we derive multiple distortions of a single sample and thus increase the positive sample diversity. Consequently, using multiple positive samples with enhanced diversity further improves contrastive learning due to better alignment. Extensive experiments on seven semantic textual similarity tasks show our method achieves consistent improvement over the contrastive learning baseline and sets new states of the art, e.g., 78.78% (+2.53% based on BERTba) Spearman correlation on STS tasks.