{"id":3354,"date":"2024-11-22T17:00:06","date_gmt":"2024-11-22T09:00:06","guid":{"rendered":"https:\/\/changjinyuan.com\/?p=3354"},"modified":"2024-12-28T22:51:30","modified_gmt":"2024-12-28T14:51:30","slug":"ai-q-he-l-liu-s-xu-z-2022-bype-vae-bayesian-pseudocoresets-exemplar-vae-neural-information-processing-systems-neurips","status":"publish","type":"post","link":"https:\/\/changjinyuan.com\/index.php\/publications\/publications-all\/3354\/","title":{"rendered":"Ai, Q., He, L., \u5218\u53f2\u6bd3, & Xu, Z. (2022). ByPE-VAE: Bayesian pseudocoresets exemplar VAE. Neural Information Processing Systems (NeurIPS)."},"content":{"rendered":"

Recent studies show that advanced priors play a major role in deep generativemodels. Exemplar VAE, as a variant of VAE with an exemplar-based prior, hasachieved impressive results. However, due to the nature of model design, anexemplar-based model usually requires vast amounts of data to participate in training, which leads to huge computational complexity. To address this issue, wepropose Bayesian Pseudocoresets Exemplar VAE (ByPE-VAE), a new variant of VAE with a prior based on Bayesian pseudocoreset. The proposed prior is condi.tioned on a small-scale pseudocoreset rather than the whole dataset for reducingthe computational cost and avoiding overfitting. Simultaneously, we obtain theoptimal pseudocoreset via a stochastic optimization algorithm during VAE trainingaiming to minimize the Kullback-Leibler divergence between the prior based onthe pseudocoreset and that based on the whole dataset. Experimental results showthat ByPE-VAE can achieve competitive improvements over the state-of-the-artVAEs in the tasks of density estimation, representation learning, and generativedata augmentation. Particularly, on a basic VAE architecture, ByPE-VAE is up to 3times faster than Exemplar VAE while almost holding the performance. Code isavailable at https:\/\/github.com\/Aiqz\/ByPE-VAE.<\/p>\r\n\r\n