Amortized learning of neural causal representations
arXiv:2008.09301
Abstract
Causal models can compactly and efficiently encode the data-generating process under all interventions and hence may generalize better under changes in distribution. These models are often represented as Bayesian networks and learning them scales poorly with the number of variables. Moreover, these approaches cannot leverage previously learned knowledge to help with learning new causal models. In order to tackle these challenges, we represent a novel algorithm called \textit{causal relational networks} (CRN) for learning causal models using neural networks. The CRN represent causal models using continuous representations and hence could scale much better with the number of variables. These models also take in previously learned information to facilitate learning of new causal models. Finally, we propose a decoding-based metric to evaluate causal models with continuous representations. We test our method on synthetic data achieving high accuracy and quick adaptation to previously unseen causal models.
ICLR 2020 causal learning for decision making workshop
References in corpus (12)
- Adam: A Method for Stochastic Optimization
- Characterization and Greedy Learning of Interventional Markov Equivalence Classes of Directed Acyclic Graphs
- Causal Discovery from a Mixture of Experimental and Observational Data
- A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms
- Causality for Machine Learning
- Causal Reasoning from Meta-reinforcement Learning
- Recurrent Independent Mechanisms
- Identifiability of Causal Graphs using Functional Models
- Causal Induction from Visual Observations for Goal Directed Tasks
- Learning Neural Causal Models from Unknown Interventions
- On the Number of Experiments Sufficient and in the Worst Case Necessary to Identify All Causal Relations Among N Variables
- Causal Generative Neural Networks