ViVA: Semi-supervised visualization via variational autoencoders

Sungtae An, Shenda Hong, Jimeng Sun

Research output: Chapter in Book/Report/Conference proceedingConference contribution


Visualizing latent embeddings is a popular approach to explain classification models, including deep neural networks. However, existing visualization methods such as t-distributed Stochastic Neighbor Embedding (t-SNE) and Uniform Manifold Approximation Projection (UMAP) are often used as a postprocessing step which is independent of the classification models. The resulting visualization can be misaligned with the classification models. In this paper, we propose ViVA, a novel method for semi-supervised Visualization via Variational Autoencoders. ViVA learns from both unlabeled and labeled data by jointly optimizing both visualization loss and classification loss. As a parameterized model using neural networks, ViVA can easily project new data to the same embedding space. Experiments show that ViVA can achieve better visualization quality as well as classification accuracy on multiple challenging datasets compared to several visualization baselines, including t-SNE and UMAP.

Original languageEnglish (US)
Title of host publicationProceedings - 20th IEEE International Conference on Data Mining, ICDM 2020
EditorsClaudia Plant, Haixun Wang, Alfredo Cuzzocrea, Carlo Zaniolo, Xindong Wu
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages10
ISBN (Electronic)9781728183169
StatePublished - Nov 2020
Event20th IEEE International Conference on Data Mining, ICDM 2020 - Virtual, Sorrento, Italy
Duration: Nov 17 2020Nov 20 2020

Publication series

NameProceedings - IEEE International Conference on Data Mining, ICDM
ISSN (Print)1550-4786


Conference20th IEEE International Conference on Data Mining, ICDM 2020
CityVirtual, Sorrento


  • Semi-supervised learning
  • Variational autoencoder
  • Visualization

ASJC Scopus subject areas

  • General Engineering


Dive into the research topics of 'ViVA: Semi-supervised visualization via variational autoencoders'. Together they form a unique fingerprint.

Cite this