Improving Representation Learning in Autoencoders via Multidimensional Interpolation and Dual Regularizations

Sheng Qian, Guanyue Li, Wen-Ming Cao, Cheng Liu, Si Wu*, Hau San Wong

*Corresponding author for this work

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

10 Citations (Scopus)

Abstract

Autoencoders enjoy a remarkable ability to learn data representations. Research on autoencoders shows that the effectiveness of data interpolation can reflect the performance of representation learning. However, existing interpolation methods in autoencoders do not have enough capability of traversing a possible region between datapoints on a data manifold, and the distribution of interpolated latent representations is not considered. To address these issues, we aim to fully exert the potential of data interpolation and further improve representation learning in autoencoders. Specifically, we propose a multidimensional interpolation approach to increase the capability of data interpolation by setting random interpolation coefficients for each dimension of the latent representations. In addition, we regularize autoencoders in both the latent and data spaces, by imposing a prior on the latent representations in the Maximum Mean Discrepancy (MMD) framework and encouraging generated datapoints to be realistic in the Generative Adversarial Network (GAN) framework. Compared to representative models, our proposed approach has empirically shown that representation learning exhibits better performance on downstream tasks on multiple benchmarks.
Original languageEnglish
Title of host publicationProceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI-19)
PublisherInternational Joint Conferences on Artificial Intelligence
Pages3268-3274
ISBN (Electronic)9780999241141
DOIs
Publication statusPublished - Aug 2019
Event28th International Joint Conference on Artificial Intelligence (IJCAI-19) - , Macao
Duration: 10 Aug 201916 Aug 2019
http://ijcai19.org/
https://www.ijcai.org/proceedings/2019/

Publication series

NameIJCAI International Joint Conference on Artificial Intelligence
ISSN (Print)1045-0823

Conference

Conference28th International Joint Conference on Artificial Intelligence (IJCAI-19)
Abbreviated titleIJCAI 2019
Country/TerritoryMacao
Period10/08/1916/08/19
Internet address

Fingerprint

Dive into the research topics of 'Improving Representation Learning in Autoencoders via Multidimensional Interpolation and Dual Regularizations'. Together they form a unique fingerprint.

Cite this