Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.20330 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908380521562112 |
|---|---|
| author | Song, Yunfu Ou, Zhijian |
| author_facet | Song, Yunfu Ou, Zhijian |
| contents | Our examination of deep generative models (DGMs) developed for semi-supervised learning (SSL), mainly GANs and VAEs, reveals two problems. First, mode missing and mode covering phenomenons are observed in genertion with GANs and VAEs. Second, there exists an awkward conflict between good classification and good generation in SSL by employing directed generative models. To address these problems, we formally present joint-stochastic-approximation random fields (JRFs) -- a new family of algorithms for building deep undirected generative models, with application to SSL. It is found through synthetic experiments that JRFs work well in balancing mode covering and mode missing, and match the empirical data distribution well. Empirically, JRFs achieve good classification results comparable to the state-of-art methods on widely adopted datasets -- MNIST, SVHN, and CIFAR-10 in SSL, and simultaneously perform good generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_20330 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Joint-stochastic-approximation Random Fields with Application to Semi-supervised Learning Song, Yunfu Ou, Zhijian Machine Learning Our examination of deep generative models (DGMs) developed for semi-supervised learning (SSL), mainly GANs and VAEs, reveals two problems. First, mode missing and mode covering phenomenons are observed in genertion with GANs and VAEs. Second, there exists an awkward conflict between good classification and good generation in SSL by employing directed generative models. To address these problems, we formally present joint-stochastic-approximation random fields (JRFs) -- a new family of algorithms for building deep undirected generative models, with application to SSL. It is found through synthetic experiments that JRFs work well in balancing mode covering and mode missing, and match the empirical data distribution well. Empirically, JRFs achieve good classification results comparable to the state-of-art methods on widely adopted datasets -- MNIST, SVHN, and CIFAR-10 in SSL, and simultaneously perform good generation. |
| title | Joint-stochastic-approximation Random Fields with Application to Semi-supervised Learning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2505.20330 |