DeepAI AI Chat
Log In Sign Up

Principled Knowledge Extrapolation with GANs

by   Ruili Feng, et al.

Human can extrapolate well, generalize daily knowledge into unseen scenarios, raise and answer counterfactual questions. To imitate this ability via generative models, previous works have extensively studied explicitly encoding Structural Causal Models (SCMs) into architectures of generator networks. This methodology, however, limits the flexibility of the generator as they must be carefully crafted to follow the causal graph, and demands a ground truth SCM with strong ignorability assumption as prior, which is a nontrivial assumption in many real scenarios. Thus, many current causal GAN methods fail to generate high fidelity counterfactual results as they cannot easily leverage state-of-the-art generative models. In this paper, we propose to study counterfactual synthesis from a new perspective of knowledge extrapolation, where a given knowledge dimension of the data distribution is extrapolated, but the remaining knowledge is kept indistinguishable from the original distribution. We show that an adversarial game with a closed-form discriminator can be used to address the knowledge extrapolation problem, and a novel principal knowledge descent method can efficiently estimate the extrapolated distribution through the adversarial game. Our method enjoys both elegant theoretical guarantees and superior performance in many scenarios.


page 1

page 6

page 7

page 8

page 15

page 16

page 17

page 18


De-Biasing Generative Models using Counterfactual Methods

Variational autoencoders (VAEs) and other generative methods have garner...

Counterfactual Identifiability of Bijective Causal Models

We study counterfactual identifiability in causal models with bijective ...

Counterfactual Generative Models for Time-Varying Treatments

Estimating average causal effects is a common practice to test new treat...

Explaining Visual Models by Causal Attribution

Model explanations based on pure observational data cannot compute the e...

Counterfactual Edits for Generative Evaluation

Evaluation of generative models has been an underrepresented field despi...

Hypothesis Testing using Causal and Causal Variational Generative Models

Hypothesis testing and the usage of expert knowledge, or causal priors, ...

Finding Needles in Haystack: Formal Generative Models for Efficient Massive Parallel Simulations

The increase in complexity of autonomous systems is accompanied by a nee...