Var-JEPA: A Variational Formulation of the Joint-Embedding Predictive Architecture -- Bridging Predictive and Generative Self-Supervised Learning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910061454950400 |
|---|---|
| author | Gögl, Moritz Yau, Christopher |
| author_facet | Gögl, Moritz Yau, Christopher |
| contents | The Joint-Embedding Predictive Architecture (JEPA) is often seen as a non-generative alternative to likelihood-based self-supervised learning, emphasizing prediction in representation space rather than reconstruction in observation space. We argue that the resulting separation from probabilistic generative modeling is largely rhetorical rather than structural: the canonical JEPA design, coupled encoders with a context-to-target predictor, mirrors the variational posteriors and learned conditional priors obtained when variational inference is applied to a particular class of coupled latent-variable models, and standard JEPA can be viewed as a deterministic specialization in which regularization is imposed via architectural and training heuristics rather than an explicit likelihood. Building on this view, we derive the Variational JEPA (Var-JEPA), which makes the latent generative structure explicit by optimizing a single Evidence Lower Bound (ELBO). This yields meaningful representations without ad-hoc anti-collapse regularizers and allows principled uncertainty quantification in the latent space. We instantiate the framework for tabular data (Var-T-JEPA) and achieve strong representation learning and downstream performance, consistently improving over T-JEPA while remaining competitive with strong raw-feature baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_20111 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Var-JEPA: A Variational Formulation of the Joint-Embedding Predictive Architecture -- Bridging Predictive and Generative Self-Supervised Learning Gögl, Moritz Yau, Christopher Machine Learning Artificial Intelligence The Joint-Embedding Predictive Architecture (JEPA) is often seen as a non-generative alternative to likelihood-based self-supervised learning, emphasizing prediction in representation space rather than reconstruction in observation space. We argue that the resulting separation from probabilistic generative modeling is largely rhetorical rather than structural: the canonical JEPA design, coupled encoders with a context-to-target predictor, mirrors the variational posteriors and learned conditional priors obtained when variational inference is applied to a particular class of coupled latent-variable models, and standard JEPA can be viewed as a deterministic specialization in which regularization is imposed via architectural and training heuristics rather than an explicit likelihood. Building on this view, we derive the Variational JEPA (Var-JEPA), which makes the latent generative structure explicit by optimizing a single Evidence Lower Bound (ELBO). This yields meaningful representations without ad-hoc anti-collapse regularizers and allows principled uncertainty quantification in the latent space. We instantiate the framework for tabular data (Var-T-JEPA) and achieve strong representation learning and downstream performance, consistently improving over T-JEPA while remaining competitive with strong raw-feature baselines. |
| title | Var-JEPA: A Variational Formulation of the Joint-Embedding Predictive Architecture -- Bridging Predictive and Generative Self-Supervised Learning |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2603.20111 |