# Self-supervised Learning from a Multi-view Perspective

arXiv: https://arxiv.org/abs/2006.05576 · HTML: https://mlsanity.com/paper/2006.05576/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jun 2020.

## Built on by (most cited first, 19 of 19)

- [Toward Understanding the Feature Learning Process of Self-supervised Contrastive Learning](https://mlsanity.com/paper/2105.15134/) (2021)
- [Self-supervised Representation Learning with Relative Predictive Coding](https://mlsanity.com/paper/2103.11275/) (2021)
- [Understanding Transferable Representation Learning and Zero-shot Transfer in CLIP](https://mlsanity.com/paper/2310.00927/) (2023)
- [Generalization Analysis for Contrastive Representation Learning](https://mlsanity.com/paper/2302.12383/) (2023)
- [ClaSP -- Parameter-free Time Series Segmentation](https://mlsanity.com/paper/2207.13987/) (2022)
- [Towards Understanding Why Mask-Reconstruction Pretraining Helps in Downstream Tasks](https://mlsanity.com/paper/2206.03826/) (2022)
- [An Empirical Study on Disentanglement of Negative-free Contrastive Learning](https://mlsanity.com/paper/2206.04756/) (2022)
- [Identifiable Causal Representation Learning: Unsupervised, Multi-View, and Multi-Environment](https://mlsanity.com/paper/2406.13371/) (2024)
- [Decoupled Self-supervised Learning for Non-Homophilous Graphs](https://mlsanity.com/paper/2206.03601/) (2022)
- [Measuring the Interpretability of Unsupervised Representations via Quantized Reverse Probing](https://mlsanity.com/paper/2209.03268/) (2022)
- [An Empirical Study and Analysis on Open-Set Semi-Supervised Learning](https://mlsanity.com/paper/2101.08237/) (2021)
- [What Makes for Robust Multi-Modal Models in the Face of Missing Modalities?](https://mlsanity.com/paper/2310.06383/) (2023)
- [A Tale of Two Classes: Adapting Supervised Contrastive Learning to Binary Imbalanced Datasets](https://mlsanity.com/paper/2503.17024/) (2025)
- [Views Can Be Deceiving: Improved SSL Through Feature Space Augmentation](https://mlsanity.com/paper/2406.18562/) (2024)
- [Understanding the Benefits of SimCLR Pre-Training in Two-Layer Convolutional Neural Networks](https://mlsanity.com/paper/2409.18685/) (2024)
- [Generalization Analysis for Deep Contrastive Representation Learning](https://mlsanity.com/paper/2412.12014/) (2024)
- [Foundations of Multisensory Artificial Intelligence](https://mlsanity.com/paper/2404.18976/) (2024)
- [Statistical Consistency and Generalization of Contrastive Representation Learning](https://mlsanity.com/paper/2605.02116/) (2026)
- [HRIL: Learning Multimodal Synergy via Higher-Order Tensor Modeling](https://mlsanity.com/paper/2610.12393/) (2026)

## Abstract (arXiv)

As a subset of unsupervised representation learning, self-supervised representation learning adopts self-defined signals as supervision and uses the learned representation for downstream tasks, such as object detection and image captioning. Many proposed approaches for self-supervised learning follow naturally a multi-view perspective, where the input (e.g., original images) and the self-supervised signals (e.g., augmented images) can be seen as two redundant views of the data. Building from this multi-view perspective, this paper provides an information-theoretical framework to better understand the properties that encourage successful self-supervised learning. Specifically, we demonstrate that self-supervised learned representations can extract task-relevant information and discard task-irrelevant information. Our theoretical framework paves the way to a larger space of self-supervised learning objective design. In particular, we propose a composite objective that bridges the gap between prior contrastive and predictive learning objectives, and introduce an additional objective term to discard task-irrelevant information. To verify our analysis, we conduct controlled experiments to evaluate the impact of the composite objectives. We also explore our framework's empirical generalization beyond the multi-view perspective, where the cross-view redundancy may not be clearly observed.