Interventional Robustness of Deep Latent Variable Models

By Raphael Suter, Ðorðe Miladinovic, Stefan Bauer, Bernhard Schölkopf. 2018

28 citations recorded by the source corpus.

Subfields: Probabilistic & Bayesian Methods

How researchers see this paper

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

In Probabilistic & Bayesian Methods

Citations in the corpus

A Sober Look at the Unsupervised Learning of Disentangled Representations and their Evaluation (2020, methodology): “The FactorVAE scores and the IRS seem to be the most efficient ones, followed by DCI Disentanglement and MIG.”
Weakly-Supervised Disentanglement Without Compromises (2020, background): “The generative model (1)–(2) does not model additive noise; we assume that noise is explicitly modeled as a latent variable and its effect is manifested through g as done by (Bengio et al., 2013; Locatello et al., 2019b; Higgins et al., 2018; 2017a; Suter et al., 2019; Reed et al., 2015; LeCun et al”
Weakly Supervised Disentanglement with Guarantees (2019, methodology): “This normalization procedure is similar in spirit to the Interventional Robustness score in Suter et al. (2018).”
On the Fairness of Disentangled Representations (2019, background): “Indeed, isolating each independent factor of variation into the independent components of a representation vector should make it both interpretable and simplify downstream prediction tasks [6, 7, 29, 35, 56, 58, 60, 74, 82, 87, 89, 90, 1, 28].”
Are Disentangled Representations Helpful for Abstract Visual Reasoning? (2019, methodology): “Following the successes in learning distributed representations that efficiently encode the content of high-dimensional sensory data [44, 54, 73], recent work has focused on learning representations that are disentangled [6, 67, 66, 71, 69, 26, 27, 42, 10, 61, 16, 50, 51, 47, 9].”
Towards a Definition of Disentangled Representations (2018, background): “To date, most work on disentangling has relied on comparison with human intuition for evaluation, though a number of metrics have been proposed in the case where the ground truth factors are known [27, 65, 51, 47, 55, 72].”
Disentangling Factors of Variation Using Few Labels (2019, background): “Furthermore, by assuming to partially observe all the causal parents of x we avoid unobserved confounding between z and x which makes the structure not identifiable from observational data [49, 11, 60].”
Unsupervised Model Selection for Variational Disentangled Representation Learning (2019, background): “This opens up opportunities for counterfactual reasoning, more robust and interpretable inference and model-based planning (Higgins et al., 2018a; Suter et al., 2018).”
Structural Autoencoders Improve Representations for Generation and Transfer (2020, methodology): “…compare the performance of each of the methods using a variety of different metrics to elucidate the quality of generated samples (using our "hybrid" sampling method as well as the standard "prior" sampling): disentanglement [29, 30], fairness [31], and abstract visual reasoning capabilities [32].”
Is Independence all you need? On the Generalization of Representations Learned from Correlated Data (2020, background): “In the causality community, this is often considered a prerequisite to achieve representations which are robust to interventions upon variables determined by such models (Peters et al., 2017; Suter et al., 2019; Goyal et al., 2019).”
Disentangling Factors of Variations Using Few Labels (2020, background): “, 2018) and learning disentangled causal models (Suter et al., 2019).”