72 citations · 310 across the 41 of their papers we have counts for
41 papers
Anchor PCA
Benedikt Seiter, Anya Fries, Julius von Kügelgen +1
Principal component analysis (PCA) is one of the most widely used unsupervised dimension reduction techniques. We study PCA for data from multiple related domains. Since principal…
From Pixels to Components: Eigenvector Masking for Visual Representation Learning
Alice Bizeul, Thomas Sutter, Alain Ryser +3
Predicting masked from visible parts of an image is a powerful self-supervised approach for visual representation learning. However, the common practice of masking random patches o…
Interaction Asymmetry: A General Principle for Learning Composable Abstractions
Jack Brady, Julius von Kügelgen, Sébastien Lachapelle +3
Learning disentangled representations of concepts and re-composing them in unseen ways is crucial for generalizing to out-of-domain situations. However, the underlying properties o…
Identifiable Causal Representation Learning: Unsupervised, Multi-View, and Multi-Environment
Julius von Kügelgen
Causal models provide rich descriptions of complex systems as sets of mechanisms by which each variable is influenced by its direct causes. They support reasoning about manipulatin…
A Sparsity Principle for Partially Observable Causal Representation Learning
Danru Xu, Dingling Yao, Sébastien Lachapelle +4
Causal representation learning aims at identifying high-level causal variables from perceptual data. Most methods assume that all latent causal variables are captured in the high-d…
Independent Mechanism Analysis and the Manifold Hypothesis
Shubhangi Ghosh, Luigi Gresele, Julius von Kügelgen +2
Independent Mechanism Analysis (IMA) seeks to address non-identifiability in nonlinear Independent Component Analysis (ICA) by assuming that the Jacobian of the mixing function has…
Kernel-based independence tests for causal structure learning on functional data
Felix Laumann, Julius von Kügelgen, Junhyung Park +2
Measurements of systems taken along a continuous functional dimension, such as time or space, are ubiquitous in many fields, from the physical and biological sciences to economics…
Self-Supervised Disentanglement by Leveraging Structure in Data Augmentations
Cian Eastwood, Julius von Kügelgen, Linus Ericsson +4
Self-supervised representation learning often uses data augmentations to induce some invariance to "style" attributes of the data. However, with downstream tasks generally unknown…
Multi-View Causal Representation Learning with Partial Observability
Dingling Yao, Danru Xu, Sébastien Lachapelle +5
We present a unified framework for studying the identifiability of representations learned from simultaneously observed views, such as different data modalities. We allow a partial…
Deep Backtracking Counterfactuals for Causally Compliant Explanations
Klaus-Rudolf Kladny, Julius von Kügelgen, Bernhard Schölkopf +1
Counterfactuals answer questions of what would have been observed under altered circumstances and can therefore offer valuable insights. Whereas the classical interventional interp…
Spuriosity Didn't Kill the Classifier: Using Invariant Predictions to Harness Spurious Features
Cian Eastwood, Shashank Singh, Andrei Liviu Nicolicioiu +3
To avoid failures on out-of-distribution data, recent works have sought to extract features that have an invariant or stable relationship with the label across domains, discarding…
Causal Effect Estimation from Observational and Interventional Data Through Matrix Weighted Linear Estimators
Klaus-Rudolf Kladny, Julius von Kügelgen, Bernhard Schölkopf +1
We study causal effect estimation from a mixture of observational and interventional data in a confounded linear regression model with multivariate treatments. We show that the sta…
Nonparametric Identifiability of Causal Representations from Unknown Interventions
Julius von Kügelgen, Michel Besserve, Liang Wendong +5
We study causal representation learning, the task of inferring latent causal variables and their causal relations from high-dimensional mixtures of the variables. Prior work relies…
Provably Learning Object-Centric Representations
Jack Brady, Roland S. Zimmermann, Yash Sharma +3
Learning structured representations of the visual world in terms of objects promises to significantly improve the generalization abilities of current machine learning models. While…
Causal Component Analysis
Liang Wendong, Armin Kekić, Julius von Kügelgen +4
Independent Component Analysis (ICA) aims to recover independent latent variables from observed mixtures thereof. Causal Representation Learning (CRL) aims instead to infer causall…
Backtracking Counterfactuals
Julius von Kügelgen, Abdirisak Mohamed, Sander Beckers
Counterfactual reasoning -- envisioning hypothetical scenarios, or possible worlds, where some circumstances are different from what (f)actually occurred (counter-to-fact) -- is ub…
DCI-ES: An Extended Disentanglement Framework with Connections to Identifiability
Cian Eastwood, Andrei Liviu Nicolicioiu, Julius von Kügelgen +4
In representation learning, a common approach is to seek representations which disentangle the underlying factors of variation. Eastwood & Williams (2018) proposed three metrics fo…
Probable Domain Generalization via Quantile Risk Minimization
Cian Eastwood, Alexander Robey, Shashank Singh +4
Domain generalization (DG) seeks predictors which perform well on unseen test distributions by leveraging data drawn from multiple related training distributions or domains. To ach…
Embrace the Gap: VAEs Perform Independent Mechanism Analysis
Patrik Reizinger, Luigi Gresele, Jack Brady +6
Variational autoencoders (VAEs) are a popular framework for modeling complex data distributions; they can be efficiently trained via variational inference by maximizing the evidenc…
Active Bayesian Causal Inference
Christian Toth, Lars Lorch, Christian Knoll +4
Causal discovery and causal reasoning are classically treated as separate and consecutive tasks: one first infers the causal graph, and then uses it to estimate causal effects of i…
Causal Discovery in Heterogeneous Environments Under the Sparse Mechanism Shift Hypothesis
Ronan Perry, Julius von Kügelgen, Bernhard Schölkopf
Machine learning approaches commonly rely on the assumption of independent and identically distributed (i.i.d.) data. In reality, however, this assumption is almost always violated…
From Statistical to Causal Learning
Bernhard Schölkopf, Julius von Kügelgen
We describe basic ideas underlying research to build and understand artificially intelligent systems: from symbolic approaches via statistical learning to interventional models rel…
On Pitfalls of Identifiability in Unsupervised Learning. A Note on: "Desiderata for Representation Learning: A Causal Perspective"
Shubhangi Ghosh, Luigi Gresele, Julius von Kügelgen +2
Model identifiability is a desirable property in the context of unsupervised representation learning. In absence thereof, different models may be observationally indistinguishable…
Causal Inference Through the Structural Causal Marginal Problem
Luigi Gresele, Julius von Kügelgen, Jonas M. Kübler +3
We introduce an approach to counterfactual inference based on merging information from multiple datasets. We consider a causal reformulation of the statistical marginal problem: gi…