{"url":"/method/gmvae","slug":"gmvae","name":"GMVAE","full_name":"Gaussian Mixture Variational Autoencoder","full_name_withheld":false,"description_markdown":"**GMVAE**, or **Gaussian Mixture Variational Autoencoder**, is a stochastic regularization layer for [transformers](https://paperswithcode.com/methods/category/transformers). A GMVAE layer is trained using a 700-dimensional internal representation of the first MLP layer. For every output from the first MLP layer, the GMVAE layer first computes a latent low-dimensional representation sampling from the GMVAE posterior distribution to then provide at the output a reconstruction sampled from a generative model.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Regularizing Transformers With Deep Probabilistic Layers","paper":"/paper/regularizing-transformers-with-deep","first_author":"Aurora Cobo Aguilera","n_authors":4,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/regularizing-transformers-with-deep"},"source":{"url":"https://arxiv.org/abs/2108.10764v1","title":"Regularizing Transformers With Deep Probabilistic Layers","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Regularization","url":"/methods/category/regularization","pwc_aliases":[]}],"n_papers_tagged":5,"archive_num_papers":5,"papers_newest_first":[{"paper":null,"title":"Physically Interpretable Representation and Controlled Generation for Turbulence Data","date":"2025-01-31","arxiv_id":"2502.02605","n_code_links":0,"syntology":null},{"paper":"/paper/marta-a-model-for-the-automatic-phonemic","title":"MARTA: a model for the automatic phonemic grouping of the parkinsonian speech","date":"2024-03-19","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"title":"Latent Combinational Game Design","date":"2022-06-28","arxiv_id":"2206.14203","n_code_links":0,"syntology":null},{"paper":null,"title":"Variational embedding of protein folding simulations using gaussian mixture variational autoencoders","date":"2021-08-27","arxiv_id":"2108.12493","n_code_links":0,"syntology":null},{"paper":"/paper/regularizing-transformers-with-deep","title":"Regularizing Transformers With Deep Probabilistic Layers","date":"2021-08-23","arxiv_id":"2108.10764","n_code_links":0,"syntology":null}],"papers_shown":5,"tasks":[{"task":"/task/dimensionality-reduction","name":"Dimensionality Reduction","papers":2},{"task":"/task/benchmarking","name":"Benchmarking","papers":1},{"task":"/task/classification-1","name":"Classification","papers":1},{"task":"/task/decoder","name":"Decoder","papers":1},{"task":"/task/game-design","name":"Game Design","papers":1},{"task":"/task/metric-learning","name":"Metric Learning","papers":1},{"task":"/task/protein-folding","name":"Protein Folding","papers":1}],"tasks_shown":7,"n_tasks":7,"usage_by_year":[{"year":"2021","papers":2},{"year":"2022","papers":1},{"year":"2024","papers":1},{"year":"2025","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/gmvae"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}