English
Related papers

Related papers: Debiasing Concept-based Explanations with Causal A…

200 papers

Decisions in organizations are about evaluating alternatives and choosing the one that would best serve organizational goals. To the extent that the evaluation of alternatives could be formulated as a predictive task with appropriate…

Human-Computer Interaction · Computer Science 2022-06-30 Charles Wan , Rodrigo Belo , Leid Zejnilović

Image classification models tend to make decisions based on peripheral attributes of data items that have strong correlation with a target variable (i.e., dataset bias). These biased models suffer from the poor generalization capability…

Machine Learning · Computer Science 2021-10-26 Jungsoo Lee , Eungyeup Kim , Juyoung Lee , Jihyeon Lee , Jaegul Choo

Debiased collaborative filtering aims to learn an unbiased prediction model by removing different biases in observational datasets. To solve this problem, one of the simple and effective methods is based on the propensity score, which…

Information Retrieval · Computer Science 2024-05-01 Haoxuan Li , Chunyuan Zheng , Yanghao Xiao , Peng Wu , Zhi Geng , Xu Chen , Peng Cui

Unobserved confounding is a major hurdle for causal inference from observational data. Confounders---the variables that affect both the causes and the outcome---induce spurious non-causal correlations between the two. Wang & Blei (2018)…

Machine Learning · Statistics 2019-05-31 Yixin Wang , David M. Blei

Stance detection models may tend to rely on dataset bias in the text part as a shortcut and thus fail to sufficiently learn the interaction between the targets and texts. Recent debiasing methods usually treated features learned by small…

Computation and Language · Computer Science 2022-12-21 Jianhua Yuan , Yanyan Zhao , Bing Qin

Using observational data to estimate the effect of a treatment is a powerful tool for decision-making when randomized experiments are infeasible or costly. However, observational data often yields biased estimates of treatment effects,…

Methodology · Statistics 2022-03-01 Tobias Hatt , Stefan Feuerriegel

This paper addresses the problem of measurement errors in causal inference and highlights several algebraic and graphical methods for eliminating systematic bias induced by such errors. In particulars, the paper discusses the control of…

Methodology · Statistics 2012-03-19 Judea Pearl

Traditional deep learning interpretability methods which are suitable for model users cannot explain network behaviors at the global level and are inflexible at providing fine-grained explanations. As a solution, concept-based explanations…

Human-Computer Interaction · Computer Science 2022-10-26 Jinbin Huang , Aditi Mishra , Bum Chul Kwon , Chris Bryan

Causal inference with observational data can be performed under an assumption of no unobserved confounders (unconfoundedness assumption). There is, however, seldom clear subject-matter or empirical evidence for such an assumption. We…

Methodology · Statistics 2023-11-13 Minna Genbäck , Xavier de Luna

We study causal discovery from observational data in linear Gaussian systems affected by \emph{mixed latent confounding}, where some unobserved factors act broadly across many variables while others influence only small subsets. This…

Machine Learning · Computer Science 2026-01-01 Amir Asiaee , Samhita Pal , James O'quinn , James P. Long

We address the problem of estimating causal effects from observational data in the presence of network confounding, a setting where both treatment assignment and observed outcomes of individuals may be influenced by their neighbors within a…

Machine Learning · Computer Science 2026-03-24 Abhishek Dalvi , Neil Ashtekar , Vasant Honavar

Concept bottleneck models are interpretable predictive models that are often used in domains where model trust is a key priority, such as healthcare. They identify a small number of human-interpretable concepts in the data, which they then…

Machine Learning · Computer Science 2024-12-25 Katrina Brown , Marton Havasi , Finale Doshi-Velez

Concept-based explanations translate the internal representations of deep learning models into a language that humans are familiar with: concepts. One popular method for finding concepts is Concept Activation Vectors (CAVs), which are…

Machine Learning · Computer Science 2025-02-14 Angus Nicolson , Lisa Schut , J. Alison Noble , Yarin Gal

The pursuit of interpretable artificial intelligence has led to significant advancements in the development of methods that aim to explain the decision-making processes of complex models, such as deep learning systems. Among these methods,…

Machine Learning · Computer Science 2024-10-29 Yihao Zhang

Estimating the effect of intervention from observational data while accounting for confounding variables is a key task in causal inference. Oftentimes, the confounders are unobserved, but we have access to large amounts of additional…

Machine Learning · Computer Science 2022-12-13 Shachi Deshpande , Kaiwen Wang , Dhruv Sreenivas , Zheng Li , Volodymyr Kuleshov

Evaluating hypothetical statements about how the world would be had a different course of action been taken is arguably one key capability expected from modern AI systems. Counterfactual reasoning underpins discussions in fairness, the…

Machine Learning · Computer Science 2022-10-04 Kevin Xia , Yushu Pan , Elias Bareinboim

Parametric causal modelling techniques rarely provide functionality for counterfactual estimation, often at the expense of modelling complexity. Since causal estimations depend on the family of functions used to model the data, simplistic…

Machine Learning · Statistics 2020-06-16 Álvaro Parafita , Jordi Vitrià

Causal graphs (CGs) are compact representations of the knowledge of the data generating processes behind the data distributions. When a CG is available, e.g., from the domain knowledge, we can infer the conditional independence (CI)…

Machine Learning · Computer Science 2021-08-18 Takeshi Teshima , Masashi Sugiyama

Many applications of computational social science aim to infer causal conclusions from non-experimental data. Such observational data often contains confounders, variables that influence both potential causes and potential effects.…

Computation and Language · Computer Science 2020-05-05 Katherine A. Keith , David Jensen , Brendan O'Connor

Automated predictions require explanations to be interpretable by humans. One type of explanation is a rationale, i.e., a selection of input features such as relevant text snippets from which the model computes the outcome. However, a…

Computation and Language · Computer Science 2021-05-12 Diego Antognini , Boi Faltings