English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  A theory of independent mechanisms for extrapolation in generative models

Besserve, M., Sun, R., Janzing, D., & Schölkopf, B. (2021). A theory of independent mechanisms for extrapolation in generative models. In Proceedings of the AAAI Conference on Artificial Intelligence (pp. 6741-6749).

Item is

Basic

show hide
Genre: Conference Paper

Files

show Files

Locators

show
hide
Description:
-
OA-Status:

Creators

show
hide
 Creators:
Besserve, M1, 2, Author           
Sun, R3, Author
Janzing, D3, Author           
Schölkopf, B3, Author           
Affiliations:
1Department Physiology of Cognitive Processes, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497798              
2Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794              
3Dept. Empirical Inference, Max Planck Institute for Intelligent Systems, Max Planck Society, ou_1497647              

Content

show
hide
Free keywords: -
 Abstract: Deep generative models reproduce complex empirical data but cannot extrapolate to novel environments. An intuitive idea to promote extrapolation capabilities is to enforce the architecture to have the modular structure of a causal graphical model, where one can intervene on each module independently of the others in the graph. We develop a framework to formalize this intuition, using the principle of Independent Causal Mechanisms, and show how over-parameterization of generative neural networks can hinder extrapolation capabilities. Our experiments on the generation of human faces shows successive layers of a generator architecture implement independent mechanisms to some extent, allowing meaningful extrapolations. Finally, we illustrate that independence of mechanisms may be enforced during training to improve extrapolation.

Details

show
hide
Language(s):
 Dates: 2021-05
 Publication Status: Published online
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: -
 Degree: -

Event

show
hide
Title: 35th AAAI Conference on Artificial Intelligence: A Virtual Conference
Place of Event: -
Start-/End Date: 2021-02-02 - 2021-02-09

Legal Case

show

Project information

show

Source 1

show
hide
Title: Proceedings of the AAAI Conference on Artificial Intelligence
Source Genre: Proceedings
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: 35 (8) Sequence Number: - Start / End Page: 6741 - 6749 Identifier: -