2021/06/24 by Sun Sun, Hongyu Guo, Sun, Sun +1 · 1 citation
Computer Science · Mathematics · #Artificial Intelligence (cs.AI) #Artificial intelligence #Computer Vision and Pattern Recognition (cs.CV) #Computer science #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Machine Learning (cs.LG) #Mathematics #Topological and Geometric Data Analysis #cs.AI #cs.CV #cs.LG
paper · pdf · doi:10.48550/arxiv.2106.13024
published in arXiv (Cornell University) (Cornell University) · Accepted by UAI2021
arxiv created 2021/06/24 · openalex publication_date 2021/06/24 · arxiv updated 2021/06/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Leveraging the framework of Optimal Transport, we introduce a new family of generative autoencoders with a learnable prior, called Symmetric Wasserstein Autoencoders (SWAEs). We propose to symmetrically match the joint distributions of the observed data and the latent representation induced by the encoder and the decoder. The resulting algorithm jointly optimizes the modelling losses in both the data and the latent spaces with the loss in the data space leading to the denoising effect. With the symmetric treatment of the data and the latent representation, the algorithm implicitly preserves the local structure of the data in the latent space. To further improve the quality of the latent representation, we incorporate a reconstruction loss into the objective, which significantly benefits both the generation and reconstruction. We empirically show the superior performance of SWAEs over the state-of-the-art generative autoencoders in terms of classification, reconstruction, and generation.