English
Related papers

Related papers: Addressing divergent representations from causal i…

200 papers

Causal disentanglement aims to uncover a representation of data using latent variables that are interrelated through a causal model. Such a representation is identifiable if the latent model that explains the data is unique. In this paper,…

Neural networks have greatly boosted performance in computer vision by learning powerful representations of input data. The drawback of end-to-end training for maximal overall performance are black-box models whose hidden representations…

Computer Vision and Pattern Recognition · Computer Science 2020-04-29 Patrick Esser , Robin Rombach , Björn Ommer

This paper studies the causal representation learning problem when the latent causal variables are observed indirectly through an unknown linear transformation. The objectives are: (i) recovering the unknown linear transformation (up to…

Machine Learning · Statistics 2023-05-02 Burak Varici , Emre Acarturk , Karthikeyan Shanmugam , Abhishek Kumar , Ali Tajer

In many problems, the measured variables (e.g., image pixels) are just mathematical functions of the latent causal variables (e.g., the underlying concepts or objects). For the purpose of making predictions in changing environments or…

Machine Learning · Computer Science 2024-08-13 Kun Zhang , Shaoan Xie , Ignavier Ng , Yujia Zheng

Deep neural networks can obtain impressive performance on various tasks under the assumption that their training domain is identical to their target domain. Performance can drop dramatically when this assumption does not hold. One…

Machine Learning · Computer Science 2024-10-10 Gaël Gendron , Michael Witbrock , Gillian Dobbie

Predictive models can fail to generalize from training to deployment environments because of dataset shift, posing a threat to model reliability and the safety of downstream decisions made in practice. Instead of using samples from the…

Machine Learning · Statistics 2018-08-10 Adarsh Subbaswamy , Suchi Saria

Understanding predictions made by deep neural networks is notoriously difficult, but also crucial to their dissemination. As all machine learning based methods, they are as good as their training data, and can also capture unwanted biases.…

Computation and Language · Computer Science 2022-11-15 Amir Feder , Nadav Oved , Uri Shalit , Roi Reichart

Identifying variables responsible for changes to a biological system enables applications in drug target discovery and cell engineering. Given a pair of observational and interventional datasets, the goal is to isolate the subset of…

Machine Learning · Computer Science 2025-06-02 Menghua Wu , Umesh Padia , Sean H. Murphy , Regina Barzilay , Tommi Jaakkola

Causal representation learning has attracted significant research interest during the past few years, as a means for improving model generalization and robustness. Causal representations of interventional image pairs (also called…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Panagiotis Alimisis , Christos Diou

The concept of causal abstraction got recently popularised to demystify the opaque decision-making processes of machine learning models; in short, a neural network can be abstracted as a higher-level algorithm if there exists a function…

Machine Learning · Computer Science 2025-11-13 Denis Sutter , Julian Minder , Thomas Hofmann , Tiago Pimentel

Mechanistic Interpretability aims to understand neural networks through causal explanations. We argue for the Explanatory View Hypothesis: that Mechanistic Interpretability research is a principled approach to understanding models because…

Machine Learning · Computer Science 2025-05-05 Kola Ayonrinde , Louis Jaburi

In causal inference, interference occurs when the treatment of one unit may affect the outcomes of other units. The goal of this work is to serve as a guide to the use of linear outcome modeling for estimating causal effects in settings…

Methodology · Statistics 2026-04-01 Eric Tong , Salvador V. Balkus

The study of causal abstractions bridges two integral components of human intelligence: the ability to determine cause and effect, and the ability to interpret complex patterns into abstract concepts. Formally, causal abstraction frameworks…

Machine Learning · Computer Science 2025-09-29 Kevin Xia , Elias Bareinboim

As input data distributions evolve, the predictive performance of machine learning models tends to deteriorate. In practice, new input data tend to come without target labels. Then, state-of-the-art techniques model input data distributions…

Machine Learning · Computer Science 2023-09-08 Carlos Mougan , Klaus Broelemann , David Masip , Gjergji Kasneci , Thanassis Thiropanis , Steffen Staab

While probabilistic models are an important tool for studying causality, doing so suffers from the intractability of inference. As a step towards tractable causal models, we consider the problem of learning interventional distributions…

Machine Learning · Computer Science 2021-10-26 Matej Zečević , Devendra Singh Dhami , Athresh Karanam , Sriraam Natarajan , Kristian Kersting

Most efforts in interpretability in deep learning have focused on (1) extracting explanations of a specific downstream task in relation to the input features and (2) imposing constraints on the model, often at the expense of predictive…

Machine Learning · Computer Science 2022-02-22 Marco Bertolini , Djork-Arné Clevert , Floriane Montanari

Mechanistic interpretability (MI) aims to understand AI models by reverse-engineering the exact algorithms neural networks learn. Most works in MI so far have studied behaviors and capabilities that are trivial and token-aligned. However,…

Machine Learning · Computer Science 2024-07-15 Satvik Golechha , James Dao

In the context of having an instrumental variable, the standard practice in causal inference begins by targeting an effect of interest and proceeds by formulating assumptions enabling its identification. We turn this around by adhering to…

Statistics Theory · Mathematics 2026-05-25 Carlos García Meixide , Mark J. van der Laan

In designing generative models, it is commonly believed that in order to learn useful latent structure, we face a fundamental tension between expressivity and structure. In this paper we challenge this view by proposing a new approach to…

Machine Learning · Statistics 2026-04-03 Alex Markham , Isaac Hirsch , Jeri A. Chang , Liam Solus , Bryon Aragam

The success of neural networks builds to a large extent on their ability to create internal knowledge representations from real-world high-dimensional data, such as images, sound, or text. Approaches to extract and present these…

Artificial Intelligence · Computer Science 2023-01-03 Lars Holmberg , Paul Davidsson , Per Linde