GDPP: Learning Diverse Generations using Determinantal Point Processes

Mohamed Elfeki*, Camille Couprie, Morgane Rivière, Mohamed Elhoseiny

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

16 Scopus citations

Abstract

Generative models have proven to be an outstanding tool for representing high-dimensional probability distributions and generating realistic looking images. An essential characteristic of generative models is their ability to produce multimodal outputs. However, while training, they are often susceptible to mode collapse, that is models are limited in mapping input noise to only a few modes of the true data distribution. In this work, we draw inspiration from Determinantal Point Process (DPP) to propose an unsupervised penalty loss that alleviates mode collapse while producing higher quality samples. DPP is an elegant probabilistic measure used to model negative correlations within a subset and hence quantify its diversity. We use DPP kernel to model the diversity in real data as well as in synthetic data. Then, we devise an objective term that encourages generator to synthesize data with a similar diversity to real data. In contrast to previous state-of-the-art generative models that tend to use additional trainable parameters or complex training paradigms, our method docs not change the original training scheme. Embedded in an adversarial training and variational autoencoder, our Generative DPP approach shows a consistent resistance to mode-collapse on a wide-variety of synthetic data and natural image datasets including MNIST, CIFAR10, and CelcbA, while outperforming state-of-the-art methods for data-efficiency, generation quality, and convergence-time whereas being 5.8x faster than its closest competitor.

Original languageEnglish (US)
Title of host publication36th International Conference on Machine Learning, ICML 2019
PublisherInternational Machine Learning Society (IMLS)
Pages3178-3193
Number of pages16
ISBN (Electronic)9781510886988
StatePublished - 2019
Event36th International Conference on Machine Learning, ICML 2019 - Long Beach, United States
Duration: Jun 9 2019Jun 15 2019

Publication series

Name36th International Conference on Machine Learning, ICML 2019
Volume2019-June

Conference

Conference36th International Conference on Machine Learning, ICML 2019
Country/TerritoryUnited States
CityLong Beach
Period06/9/1906/15/19

Bibliographical note

Publisher Copyright:
Copyright 2019 by the author(s).

ASJC Scopus subject areas

  • Education
  • Computer Science Applications
  • Human-Computer Interaction

Fingerprint

Dive into the research topics of 'GDPP: Learning Diverse Generations using Determinantal Point Processes'. Together they form a unique fingerprint.

Cite this