# A Principled Framework for Multi-View Contrastive Learning

arXiv: https://arxiv.org/abs/2507.06979 · HTML: https://mlsanity.com/paper/2507.06979/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 51 references that are in the map.
- First posted on arXiv 9 Jul 2025.

## Builds on (most cited first, 30 of 39)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere](https://mlsanity.com/paper/2005.10242/) (2020)
- [Contrastive Multiview Coding](https://mlsanity.com/paper/1906.05849/) (2019)
- [Learning Representations by Maximizing Mutual Information Across Views](https://mlsanity.com/paper/1906.00910/) (2019)
- [Contrastive Learning with Hard Negative Samples](https://mlsanity.com/paper/2010.04592/) (2020)
- [Understanding Dimensional Collapse in Contrastive Self-supervised Learning](https://mlsanity.com/paper/2110.09348/) (2021)
- [With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2104.14548/) (2021)
- [Whitening for Self-Supervised Representation Learning](https://mlsanity.com/paper/2007.06346/) (2020)
- [On Feature Decorrelation in Self-Supervised Learning](https://mlsanity.com/paper/2105.00470/) (2021)
- [RankMe: Assessing the downstream performance of pretrained self-supervised representations by their rank](https://mlsanity.com/paper/2210.02885/) (2022)
- [Decoupled Contrastive Learning](https://mlsanity.com/paper/2110.06848/) (2021)
- [VICRegL: Self-Supervised Learning of Local Visual Features](https://mlsanity.com/paper/2210.01571/) (2022)
- [Multi-level Feature Learning for Contrastive Multi-view Clustering](https://mlsanity.com/paper/2106.11193/) (2021)
- [Dual Temperature Helps Contrastive Learning Without Many Negative Samples: Towards Understanding and Simplifying MoCo](https://mlsanity.com/paper/2203.17248/) (2022)
- [Unsupervised Feature Learning by Cross-Level Instance-Group Discrimination](https://mlsanity.com/paper/2008.03813/) (2020)
- [Contrastive Multimodal Fusion with TupleInfoNCE](https://mlsanity.com/paper/2107.02575/) (2021)
- [How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularization](https://mlsanity.com/paper/2210.06441/) (2022)
- [Drawing Multiple Augmentation Samples Per Image During Training Efficiently Decreases Test Error](https://mlsanity.com/paper/2105.13343/) (2021)
- [Grounding inductive biases in natural images:invariance stems from variations in data](https://mlsanity.com/paper/2106.05121/) (2021)
- [MERBench: A Unified Evaluation Benchmark for Multimodal Emotion Recognition](https://mlsanity.com/paper/2401.03429/) (2024)

## Built on by (most cited first, 4 of 4)

- [Toward Enhancing Representation Learning in Federated Multi-Task Settings](https://mlsanity.com/paper/2602.01626/) (2026)
- [EGA: Adapting Frozen Encoders for Vector Search with Bounded Out-of-Distribution Degradation](https://mlsanity.com/paper/2605.05674/) (2026)
- [An Analysis of Self-supervised Pre-training with Dependent Samples](https://mlsanity.com/paper/2609.05031/) (2026)
- [HRIL: Learning Multimodal Synergy via Higher-Order Tensor Modeling](https://mlsanity.com/paper/2610.12393/) (2026)

## Abstract (arXiv)

Contrastive Learning (CL), a leading paradigm in Self-Supervised Learning (SSL), typically relies on pairs of data views generated through augmentation. While multiple augmentations per instance (more than two) improve generalization in supervised learning, current CL methods handle additional views suboptimally by simply aggregating different pairwise objectives. This approach suffers from four critical limitations: (L1) it utilizes multiple optimization terms per data point resulting to conflicting objectives, (L2) it fails to model all interactions across views and data points, (L3) it inherits fundamental limitations (e.g. alignment-uniformity coupling) from pairwise CL losses, and (L4) it prevents fully realizing the benefits of increased view multiplicity observed in supervised settings. We address these limitations through two novel loss functions: MV-InfoNCE, which extends InfoNCE to incorporate all possible view interactions simultaneously in one term per data point, and MV-DHEL, which decouples alignment from uniformity across views while scaling interaction complexity with view multiplicity. Both approaches are theoretically grounded - we prove they asymptotically optimize for alignment of all views and uniformity, providing principled extensions to multi-view contrastive learning. Our empirical results on ImageNet1K and three other datasets demonstrate that our methods consistently outperform existing multi-view approaches and effectively scale with increasing view multiplicity. We also apply our objectives to multimodal data and show that, in contrast to other contrastive objectives, they can scale beyond just two modalities. Most significantly, ablation studies reveal that MV-DHEL with five or more views effectively mitigates dimensionality collapse by fully utilizing the embedding space, thereby delivering multi-view benefits observed in supervised learning.