English
Related papers

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

200 papers

Causality has traditionally been a scientific way to generate knowledge by relating causes to effects. From an imaginery point of view, causal graphs are a helpful tool for representing and infering new causal information. In previous…

Artificial Intelligence · Computer Science 2020-02-07 Eduardo C. Garrido-Merchán , C. Puente , A. Sobrino , J. A. Olivas

Causal opacity denotes the difficulty in understanding the "hidden" causal structure underlying the decisions of deep neural network (DNN) models. This leads to the inability to rely on and verify state-of-the-art DNN-based systems,…

Concept-based machine learning methods have increasingly gained importance due to the growing interest in making neural networks interpretable. However, concept annotations are generally challenging to obtain, making it crucial to leverage…

Machine Learning · Computer Science 2024-11-06 Alba Carballo-Castro , Sonia Laguna , Moritz Vandenhirtz , Julia E. Vogt

Estimating an individual's counterfactual outcomes under interventions is a challenging task for traditional causal inference and supervised learning approaches when the outcome is high-dimensional (e.g. gene expressions, facial images) and…

Machine Learning · Computer Science 2025-03-19 Yulun Wu , Louie McConnell , Claudia Iriondo

Many real-world decision-making tasks require learning causal relationships between a set of variables. Traditional causal discovery methods, however, require that all variables are observed, which is often not feasible in practical…

Methodology · Statistics 2023-06-27 Raj Agrawal , Chandler Squires , Neha Prasad , Caroline Uhler

Interpretability has become an essential topic for artificial intelligence in some high-risk domains such as healthcare, bank and security. For commonly-used tabular data, traditional methods trained end-to-end machine learning models with…

Artificial Intelligence · Computer Science 2022-08-18 Haixiao Chi , Dawei Wang , Gaojie Cui , Feng Mao , Beishui Liao

The notion of concept drift refers to the phenomenon that the distribution generating the observed data changes over time. If drift is present, machine learning models can become inaccurate and need adjustment. While there do exist methods…

Machine Learning · Computer Science 2023-03-17 Fabian Hinder , Valerie Vaquet , Johannes Brinkrolf , Barbara Hammer

Complex data usually results from the interaction of objects produced by different generating mechanisms. Here we introduce a universal, unsupervised and parameter-free model-oriented approach, based upon the seminal concept of algorithmic…

Artificial Intelligence · Computer Science 2018-09-14 Hector Zenil , Narsis A. Kiani , Allan A. Zea , Jesper Tegnér

Thanks to technological advances leading to near-continuous time observations, emerging multivariate point process data offer new opportunities for causal discovery. However, a key obstacle in achieving this goal is that many relevant…

Machine Learning · Statistics 2021-12-15 Xu Wang , Ali Shojaie

Counterfactual explanations have been successfully applied to create human interpretable explanations for various black-box models. They are handy for tasks in the image domain, where the quality of the explanations benefits from recent…

Machine Learning · Computer Science 2025-03-27 Trung Duc Ha , Sidney Bender

Concept-based Models aim to improve interpretability by predicting high-level intermediate concepts, representing a promising approach for deployment in high-risk scenarios. However, they are known to suffer from information leakage,…

Machine Learning · Computer Science 2026-03-25 Enrico Parisini , Tapabrata Chakraborti , Chris Harbron , Ben D. MacArthur , Christopher R. S. Banerji

This paper provides a method for improving tensor-based compositional distributional models of meaning by the addition of an explicit disambiguation step prior to composition. In contrast with previous research where this hypothesis has…

Computation and Language · Computer Science 2014-08-28 Dimitri Kartsaklis , Nal Kalchbrenner , Mehrnoosh Sadrzadeh

Global Climate Models (GCMs) are crucial for predicting future climate changes by simulating the Earth systems. However, the GCM Outputs exhibit systematic biases due to model uncertainties, parameterization simplifications, and inadequate…

Machine Learning · Statistics 2025-06-09 Wentao Gao , Jiuyong Li , Debo Cheng , Lin Liu , Jixue Liu , Thuc Duy Le , Xiaojing Du , Xiongren Chen , Yanchang Zhao , Yun Chen

We consider the problem of answering observational, interventional, and counterfactual queries in a causally sufficient setting where only observational data and the causal graph are available. Utilizing the recent developments in diffusion…

Machine Learning · Statistics 2024-10-11 Patrick Chao , Patrick Blöbaum , Sapan Patel , Shiva Prasad Kasiviswanathan

Learning concepts that are consistent with human perception is important for Deep Neural Networks to win end-user trust. Post-hoc interpretation methods lack transparency in the feature representations learned by the models. This work…

Computer Vision and Pattern Recognition · Computer Science 2021-05-25 Sandareka Wickramanayake , Wynne Hsu , Mong Li Lee

We study identification and estimation of causal effects in settings with panel data. Traditionally researchers follow model-based identification strategies relying on assumptions governing the relation between the potential outcomes and…

Econometrics · Economics 2022-02-18 Dmitry Arkhangelsky , Guido W. Imbens

Classifiers tend to learn a false causal relationship between an over-represented concept and a label, which can result in over-reliance on the concept and compromised classification accuracy. It is imperative to have methods in place that…

Computation and Language · Computer Science 2023-07-06 Isar Nejadgholi , Svetlana Kiritchenko , Kathleen C. Fraser , Esma Balkır

Recommendation systems aim to predict users' feedback on items not exposed to them. Confounding bias arises due to the presence of unmeasured variables (e.g., the socio-economic status of a user) that can affect both a user's exposure and…

Machine Learning · Computer Science 2023-06-16 Qing Zhang , Xiaoying Zhang , Yang Liu , Hongning Wang , Min Gao , Jiheng Zhang , Ruocheng Guo

Consider the problem of estimating the causal effect of some attribute of a text document; for example: what effect does writing a polite vs. rude email have on response time? To estimate a causal effect from observational data, we need to…

Machine Learning · Statistics 2023-02-09 Lin Gui , Victor Veitch

While machine learning models have achieved unprecedented success in real-world applications, they might make biased/unfair decisions for specific demographic groups and hence result in discriminative outcomes. Although research efforts…

Machine Learning · Computer Science 2022-12-08 Yuying Zhao , Yu Wang , Tyler Derr