English
Related papers

Related papers: Answering Causal Queries at Layer 3 with DiscoSCMs…

200 papers

Predicting counterfactual outcomes in longitudinal data, where sequential treatment decisions heavily depend on evolving patient states, is critical yet notoriously challenging due to complex time-dependent confounding and inadequate…

Machine Learning · Statistics 2026-04-15 Farbod Alinezhad , Jianfei Cao , Gary J. Young , Brady Post

Causal inference from observational data following the restricted structural causal model (SCM) framework hinges largely on the asymmetry between cause and effect from the data generating mechanisms, such as non-Gaussianity or nonlinearity.…

Methodology · Statistics 2021-09-06 Kang Du , Yu Xiang

Diffusion probabilistic models (DPMs) have become the state-of-the-art in high-quality image generation. However, DPMs have an arbitrary noisy latent space with no interpretable or controllable semantics. Although there has been significant…

Machine Learning · Computer Science 2024-08-27 Aneesh Komanduri , Chen Zhao , Feng Chen , Xintao Wu

Deep neural networks (DNNs) often struggle with out-of-distribution data, limiting their reliability in diverse realworld applications. To address this issue, domain generalization methods have been developed to learn domain-invariant…

Computer Vision and Pattern Recognition · Computer Science 2025-03-24 Jiaxi Li , Di Lin , Hao Chen , Hongying Liu , Liang Wan , Wei Feng

Answering counterfactual queries has important applications such as explainability, robustness, and fairness but is challenging when the causal variables are unobserved and the observations are non-linear mixtures of these latent variables,…

Machine Learning · Computer Science 2024-04-16 Zeyu Zhou , Ruqi Bai , Sean Kulinski , Murat Kocaoglu , David I. Inouye

Structural causal models are the basic modelling unit in Pearl's causal theory; in principle they allow us to solve counterfactuals, which are at the top rung of the ladder of causation. But they often contain latent variables that limit…

Artificial Intelligence · Computer Science 2021-11-23 Marco Zaffalon , Alessandro Antonucci , Rafael Cabañas

This paper presents a topological learning-theoretic perspective on causal inference by introducing a series of topologies defined on general spaces of structural causal models (SCMs). As an illustration of the framework we prove a…

Artificial Intelligence · Computer Science 2022-06-01 Duligur Ibeling , Thomas Icard

Heterogeneity in medical data, e.g., from data collected at different sites and with different protocols in a clinical study, is a fundamental hurdle for accurate prediction using machine learning models, as such models often fail to…

Machine Learning · Computer Science 2021-07-13 Rongguang Wang , Pratik Chaudhari , Christos Davatzikos

This paper investigates the problem of bounding counterfactual queries from an arbitrary collection of observational and experimental distributions and qualitative knowledge about the underlying data-generating model represented in the form…

Artificial Intelligence · Computer Science 2021-10-13 Junzhe Zhang , Jin Tian , Elias Bareinboim

Causal inference from observational data following the restricted structural causal models (SCM) framework hinges largely on the asymmetry between cause and effect from the data generating mechanisms, such as non-Gaussianity or…

Machine Learning · Computer Science 2024-05-30 Kang Du , Yu Xiang

Constraint-based causal discovery is widely used for learning causal structures, but heavy reliance on conditional independence (CI) testing makes it computationally expensive in high-dimensional settings. To mitigate this limitation, many…

Machine Learning · Computer Science 2026-05-12 Zheng Li , Feng Xie , Shenglan Nie , Xichen Guo , Ruxin Wang , Hao Zhang

This work presents self-rewarding sequential Monte Carlo (SMC), an inference-time scaling algorithm enabling effective sampling of masked diffusion language models (MDLMs). Our algorithm stems from the observation that most existing MDLMs…

Machine Learning · Computer Science 2026-02-03 Ziwei Luo , Ziqi Jin , Lei Wang , Lidong Bing , Thomas B. Schön

Dataset bias often leads deep learning models to exploit spurious correlations instead of task-relevant signals. We introduce the Standard Anti-Causal Model (SAM), a unifying causal framework that characterizes bias mechanisms and yields a…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Emre Kavak , Tom Nuno Wolf , Christian Wachinger

Reasoning, a crucial aspect of NLP research, has not been adequately addressed by prevailing models including Large Language Model. Conversation reasoning, as a critical component of it, remains largely unexplored due to the absence of a…

Computation and Language · Computer Science 2024-01-17 Hang Chen , Bingyu Liao , Jing Luo , Wenjing Zhu , Xinyu Yang

In this paper, we consider the problem of causal order discovery within the framework of monotonic Structural Causal Models (SCMs), which have gained attention for their potential to enable causal inference and causal discovery from…

Machine Learning · Computer Science 2024-10-29 Ali Izadi , Martin Ester

We consider the task of counterfactual estimation from observational imaging data given a known causal structure. In particular, quantifying the causal effect of interventions for high-dimensional data with neural networks remains an open…

Machine Learning · Computer Science 2022-02-22 Pedro Sanchez , Sotirios A. Tsaftaris

This paper investigates $\sim_{\mathcal{L}_3}$-identifiability, a form of complete counterfactual identifiability within the Pearl Causal Hierarchy (PCH) framework, ensuring that all Structural Causal Models (SCMs) satisfying the given…

Machine Learning · Computer Science 2025-05-06 Yikang Chen , Dehui Du

With the rapid advancement of neural language models, the deployment of over-parameterized models has surged, increasing the need for interpretable explanations comprehensible to human inspectors. Existing post-hoc interpretability methods,…

Artificial Intelligence · Computer Science 2024-11-08 Zijian Zhang , Vinay Setty , Yumeng Wang , Avishek Anand

Understanding the factors that trigger or prevent undesirable health outcomes across patient subpopulations is essential for designing targeted interventions. While randomized controlled trials and expert-led patient interviews are standard…

Artificial Intelligence · Computer Science 2026-05-28 Shishir Adhikari , Guido Muscioni , Mark Shapiro , Plamen Petrov , Elena Zheleva

Despite the success of deep learning in dermoscopy image analysis, its inherent black-box nature hinders clinical trust, motivating the use of prototypical networks for case-based visual transparency. However, inevitable selection bias in…

Image and Video Processing · Electrical Eng. & Systems 2026-03-02 Junhao Jia , Yueyi Wu , Huangwei Chen , Haodong Jing , Haishuai Wang , Jiajun Bu , Lei Wu