A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms

Tristan Deleu
Tristan Deleu
Nasim Rahaman
Nasim Rahaman
Nan Rosemary Ke
Nan Rosemary Ke
Olexa Bilaniuk
Olexa Bilaniuk

ICLR, 2020.

Cited by: 96|Views765
EI

Abstract:

We propose to use a meta-learning objective that maximizes the speed of transfer on a modified distribution to learn how to modularize acquired knowledge. In particular, we focus on how to factor a joint distribution into appropriate conditionals, consistent with the causal directions. We explain when this can work, using the assumption t...More

Code:

Data:

Your rating :
0

 

Tags
Comments