Joint Embedding vs Reconstruction: Provable Benefits of Latent Space Prediction for Self Supervised Learning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908592595009536 |
|---|---|
| author | Van Assel, Hugues Ibrahim, Mark Biancalani, Tommaso Regev, Aviv Balestriero, Randall |
| author_facet | Van Assel, Hugues Ibrahim, Mark Biancalani, Tommaso Regev, Aviv Balestriero, Randall |
| contents | Reconstruction and joint embedding have emerged as two leading paradigms in Self Supervised Learning (SSL). Reconstruction methods focus on recovering the original sample from a different view in input space. On the other hand, joint embedding methods align the representations of different views in latent space. Both approaches offer compelling advantages, yet practitioners lack clear guidelines for choosing between them. In this work, we unveil the core mechanisms that distinguish each paradigm. By leveraging closed form solutions for both approaches, we precisely characterize how the view generation process, e.g. data augmentation, impacts the learned representations. We then demonstrate that, unlike supervised learning, both SSL paradigms require a minimal alignment between augmentations and irrelevant features to achieve asymptotic optimality with increasing sample size. Our findings indicate that in scenarios where these irrelevant features have a large magnitude, joint embedding methods are preferable because they impose a strictly weaker alignment condition compared to reconstruction based methods. These results not only clarify the trade offs between the two paradigms but also substantiate the empirical success of joint embedding approaches on real world challenging datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_12477 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Joint Embedding vs Reconstruction: Provable Benefits of Latent Space Prediction for Self Supervised Learning Van Assel, Hugues Ibrahim, Mark Biancalani, Tommaso Regev, Aviv Balestriero, Randall Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Reconstruction and joint embedding have emerged as two leading paradigms in Self Supervised Learning (SSL). Reconstruction methods focus on recovering the original sample from a different view in input space. On the other hand, joint embedding methods align the representations of different views in latent space. Both approaches offer compelling advantages, yet practitioners lack clear guidelines for choosing between them. In this work, we unveil the core mechanisms that distinguish each paradigm. By leveraging closed form solutions for both approaches, we precisely characterize how the view generation process, e.g. data augmentation, impacts the learned representations. We then demonstrate that, unlike supervised learning, both SSL paradigms require a minimal alignment between augmentations and irrelevant features to achieve asymptotic optimality with increasing sample size. Our findings indicate that in scenarios where these irrelevant features have a large magnitude, joint embedding methods are preferable because they impose a strictly weaker alignment condition compared to reconstruction based methods. These results not only clarify the trade offs between the two paradigms but also substantiate the empirical success of joint embedding approaches on real world challenging datasets. |
| title | Joint Embedding vs Reconstruction: Provable Benefits of Latent Space Prediction for Self Supervised Learning |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.12477 |