A Revisit of Total Correlation in Disentangled Variational Auto-Encoder with Partial Disentanglement
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912219281752064 |
|---|---|
| author | Li, Chengrui Wang, Yunmiao Wang, Yule Li, Weihan Jaeger, Dieter Wu, Anqi |
| author_facet | Li, Chengrui Wang, Yunmiao Wang, Yule Li, Weihan Jaeger, Dieter Wu, Anqi |
| contents | A fully disentangled variational auto-encoder (VAE) aims to identify disentangled latent components from observations. However, enforcing full independence between all latent components may be too strict for certain datasets. In some cases, multiple factors may be entangled together in a non-separable manner, or a single independent semantic meaning could be represented by multiple latent components within a higher-dimensional manifold. To address such scenarios with greater flexibility, we develop the Partially Disentangled VAE (PDisVAE), which generalizes the total correlation (TC) term in fully disentangled VAEs to a partial correlation (PC) term. This framework can handle group-wise independence and can naturally reduce to either the standard VAE or the fully disentangled VAE. Validation through three synthetic experiments demonstrates the correctness and practicality of PDisVAE. When applied to real-world datasets, PDisVAE discovers valuable information that is difficult to find using fully disentangled VAEs, implying its versatility and effectiveness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_02279 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Revisit of Total Correlation in Disentangled Variational Auto-Encoder with Partial Disentanglement Li, Chengrui Wang, Yunmiao Wang, Yule Li, Weihan Jaeger, Dieter Wu, Anqi Machine Learning Neurons and Cognition A fully disentangled variational auto-encoder (VAE) aims to identify disentangled latent components from observations. However, enforcing full independence between all latent components may be too strict for certain datasets. In some cases, multiple factors may be entangled together in a non-separable manner, or a single independent semantic meaning could be represented by multiple latent components within a higher-dimensional manifold. To address such scenarios with greater flexibility, we develop the Partially Disentangled VAE (PDisVAE), which generalizes the total correlation (TC) term in fully disentangled VAEs to a partial correlation (PC) term. This framework can handle group-wise independence and can naturally reduce to either the standard VAE or the fully disentangled VAE. Validation through three synthetic experiments demonstrates the correctness and practicality of PDisVAE. When applied to real-world datasets, PDisVAE discovers valuable information that is difficult to find using fully disentangled VAEs, implying its versatility and effectiveness. |
| title | A Revisit of Total Correlation in Disentangled Variational Auto-Encoder with Partial Disentanglement |
| topic | Machine Learning Neurons and Cognition |
| url | https://arxiv.org/abs/2502.02279 |