Expressivity of parameterized and data-driven representations in quality diversity search
- We consider multi-solution optimization and generative models for the generation of diverse artifacts and the discovery of novel solutions. In cases where the domain's factors of variation are unknown or too complex to encode manually, generative models can provide a learned latent space to approximate these factors. When used as a search space, however, the range and diversity of possible outputs are limited to the expressivity and generative capabilities of the learned model. We compare the output diversity of a quality diversity evolutionary search performed in two different search spaces: 1) a predefined parameterized space and 2) the latent space of a variational autoencoder model. We find that the search on an explicit parametric encoding creates more diverse artifact sets than searching the latent space. A learned model is better at interpolating between known data points than at extrapolating or expanding towards unseen examples. We recommend using a generative model's latent space primarily to measure similarity between artifacts rather than for search and generation. Whenever a parametric encoding is obtainable, it should be preferred over a learned representation as it produces a higher diversity of solutions.
Document Type: | Conference Object |
---|---|
Language: | English |
Author: | Alexander Hagg, Sebastian Berns, Alexander Asteroth, Simon Colton, Thomas Bäck |
Parent Title (English): | Chicano, Krawiec (Eds.): GECCO '21: Genetic and Evolutionary Computation Conference, Lille, France, 10-14 July, 2021 |
Number of pages: | 9 |
First Page: | 678 |
Last Page: | 686 |
ISBN: | 978-1-4503-8350-9 |
DOI: | https://doi.org/10.1145/3449639.3459287 |
ArXiv Id: | http://arxiv.org/abs/2105.04247 |
Publisher: | Association for Computing Machinery |
Place of publication: | New York, NY, USA |
Date of first publication: | 2021/06/26 |
Copyright: | © 2021 Copyright held by the owner/author(s). Publication rights licensed to the Association for Computing Machinery. Abstracting with credit is permitted. |
Keyword: | Generative Models; Quality diversity; Variational Autoencoder |
Departments, institutes and facilities: | Fachbereich Informatik |
Institut für Technik, Ressourcenschonung und Energieeffizienz (TREE) | |
Dewey Decimal Classification (DDC): | 0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme / 004 Datenverarbeitung; Informatik |
Entry in this database: | 2021/06/30 |