Knowledge-based regularization in generative modeling

Naoya Takeishi, Yoshinobu Kawahara

研究成果: Chapter in Book/Report/Conference proceedingConference contribution

1 被引用数 (Scopus)

抄録

Prior domain knowledge can greatly help to learn generative models. However, it is often too costly to hard-code prior knowledge as a specific model architecture, so we often have to use general-purpose models. In this paper, we propose a method to incorporate prior knowledge of feature relations into the learning of general-purpose generative models. To this end, we formulate a regularizer that makes the marginals of a generative model to follow prescribed relative dependence of features. It can be incorporated into off-the-shelf learning methods of many generative models, including variational autoencoders and generative adversarial networks, as its gradients can be computed using standard backpropagation techniques. We show the effectiveness of the proposed method with experiments on multiple types of datasets and generative models.

本文言語英語
ホスト出版物のタイトルProceedings of the 29th International Joint Conference on Artificial Intelligence, IJCAI 2020
編集者Christian Bessiere
出版社International Joint Conferences on Artificial Intelligence
ページ2390-2396
ページ数7
ISBN(電子版)9780999241165
出版ステータス出版済み - 2020
イベント29th International Joint Conference on Artificial Intelligence, IJCAI 2020 - Yokohama, 日本
継続期間: 1 1 2021 → …

出版物シリーズ

名前IJCAI International Joint Conference on Artificial Intelligence
2021-January
ISSN(印刷版)1045-0823

会議

会議29th International Joint Conference on Artificial Intelligence, IJCAI 2020
国/地域日本
CityYokohama
Period1/1/21 → …

All Science Journal Classification (ASJC) codes

  • 人工知能

フィンガープリント

「Knowledge-based regularization in generative modeling」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル