A theory of independent mechanisms for extrapolation in generative models

By Michel Besserve, Rémy Sun, Dominik Janzing, Bernhard Schölkopf. 2020

28 citations recorded by the source corpus.

Generative models can be trained to emulate complex empirical data, but are they useful to make predictions in the context of previously unobserved environments? An intuitive idea to promote such extrapolation capabilities is to have the architecture of such model reflect a causal graph of the true data generating process, such that one can intervene on each node independently of the others. However, the nodes of this graph are usually unobserved, leading to overparameterization and lack of identifiability of the causal structure. We develop a theoretical framework to address this challenging situation by defining a weaker form of identifiability, based on the principle of independence of mechanisms. We demonstrate on toy examples that classical stochastic gradient descent can hinder the model's extrapolation capabilities, suggesting independence of mechanisms should be enforced explicitly during training. Experiments on deep generative models trained on real world data support these insights and illustrate how the extrapolation capabilities of such models can be leveraged.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Generative Models, Causal Inference & Discovery

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Generative Models

In Causal Inference & Discovery

Citations in the corpus

Toward Causal Representation Learning (2021, methodology): “It has recently been used for learning causal models [131], modular architectures [29], [85], and disentangled representations [159].”
Towards Causal Representation Learning (2021, neutral): “learning causal models [131], modular architectures [84, 28]”