Search Results for author: Babak Salimi

Found 19 papers, 2 papers with code

Learning from Uncertain Data: From Possible Worlds to Possible Models

no code implementations28 May 2024 Jiongli Zhu, Su Feng, Boris Glavic, Babak Salimi

We introduce an efficient method for learning linear models from uncertain data, where uncertainty is represented as a set of possible variations in the data, leading to predictive multiplicity.

Enforcing Conditional Independence for Fair Representation Learning and Causal Image Generation

no code implementations21 Apr 2024 Jensen Hwa, Qingyu Zhao, Aditya Lahiri, Adnan Masood, Babak Salimi, Ehsan Adeli

We are able to enforce conditional independence of the diffusion autoencoder latent representation with respect to any protected attribute under the equalized odds constraint and show that this approach enables causal image generation with controllable latent spaces.

Attribute Fairness +2

OTClean: Data Cleaning for Conditional Independence Violations using Optimal Transport

no code implementations4 Mar 2024 Alireza Pirhadi, Mohammad Hossein Moslemi, Alexander Cloninger, Mostafa Milani, Babak Salimi

Ensuring Conditional Independence (CI) constraints is pivotal for the development of fair and trustworthy machine learning models.

Consistent Range Approximation for Fair Predictive Modeling

1 code implementation21 Dec 2022 Jiongli Zhu, Sainyam Galhotra, Nazanin Sabri, Babak Salimi

This paper proposes a novel framework for certifying the fairness of predictive models trained on biased data.

Fairness Selection bias

Combining Counterfactuals With Shapley Values To Explain Image Models

no code implementations14 Jun 2022 Aditya Lahiri, Kamran Alipour, Ehsan Adeli, Babak Salimi

With the widespread use of sophisticated machine learning models in sensitive applications, understanding their decision-making has become an essential task.

Decision Making Explainable Artificial Intelligence (XAI)

Explaining Image Classifiers Using Contrastive Counterfactuals in Generative Latent Spaces

no code implementations10 Jun 2022 Kamran Alipour, Aditya Lahiri, Ehsan Adeli, Babak Salimi, Michael Pazzani

Despite their high accuracies, modern complex image classifiers cannot be trusted for sensitive tasks due to their unknown decision-making process and potential biases.

Attribute counterfactual +1

Interpretable Data-Based Explanations for Fairness Debugging

no code implementations17 Dec 2021 Romila Pradhan, Jiongli Zhu, Boris Glavic, Babak Salimi

We introduce Gopher, a system that produces compact, interpretable and causal explanations for bias or unexpected model behavior by identifying coherent subsets of the training data that are root-causes for this behavior.

BIG-bench Machine Learning Explainable artificial intelligence +2

Explaining Black-Box Algorithms Using Probabilistic Contrastive Counterfactuals

no code implementations22 Mar 2021 Sainyam Galhotra, Romila Pradhan, Babak Salimi

There has been a recent resurgence of interest in explainable artificial intelligence (XAI) that aims to reduce the opaqueness of AI-based decision-making systems, allowing humans to scrutinize and trust them.

Decision Making Explainable artificial intelligence +1

Through the Data Management Lens: Experimental Analysis and Evaluation of Fair Classification

1 code implementation18 Jan 2021 Maliha Tashfia Islam, Anna Fariha, Alexandra Meliou, Babak Salimi

Data management research is showing an increasing presence and interest in topics related to data and algorithmic fairness, including the topic of fair classification.

BIG-bench Machine Learning Classification +3

Causal Relational Learning

no code implementations7 Apr 2020 Babak Salimi, Harsh Parikh, Moe Kayali, Sudeepa Roy, Lise Getoor, Dan Suciu

Causal inference is at the heart of empirical research in natural and social sciences and is critical for scientific discovery and informed decision making.

Causal Inference Decision Making +1

Data Management for Causal Algorithmic Fairness

no code implementations20 Aug 2019 Babak Salimi, Bill Howe, Dan Suciu

Fairness is increasingly recognized as a critical component of machine learning systems.

BIG-bench Machine Learning Fairness +1

Capuchin: Causal Database Repair for Algorithmic Fairness

no code implementations21 Feb 2019 Babak Salimi, Luke Rodriguez, Bill Howe, Dan Suciu

However, it is the underlying data on which these systems are trained that often reflect discrimination, suggesting a database repair problem.


A Framework for Inferring Causality from Multi-Relational Observational Data using Conditional Independence

no code implementations8 Aug 2017 Sudeepa Roy, Babak Salimi

The study of causality or causal inference - how much a given treatment causally affects a given outcome in a population - goes way beyond correlation or association analysis of variables, and is critical in making sound data driven decisions and policies in a multitude of applications.

Causal Inference

Causes for Query Answers from Databases: Datalog Abduction, View-Updates, and Integrity Constraints

no code implementations6 Nov 2016 Leopoldo Bertossi, Babak Salimi

In this work we establish precise connections between QA-causality and both abductive diagnosis and the view-update problem in databases, allowing us to obtain new algorithmic and complexity results for QA-causality.

ZaliQL: A SQL-Based Framework for Drawing Causal Inference from Big Data

no code implementations12 Sep 2016 Babak Salimi, Dan Suciu

In this paper we describe a suite of techniques for expressing causal inference tasks from observational data in SQL.

Causal Inference

Causes for Query Answers from Databases, Datalog Abduction and View-Updates: The Presence of Integrity Constraints

no code implementations20 Feb 2016 Babak Salimi, Leopoldo Bertossi

In this work we further investigate connections between query-answer causality and abductive diagnosis and the view-update problem.

From Causes for Database Queries to Repairs and Model-Based Diagnosis and Back

no code implementations1 Jul 2015 Leopoldo Bertossi, Babak Salimi

In this work we establish and investigate connections between causes for query answers in databases, database repairs wrt.

Query-Answer Causality in Databases: Abductive Diagnosis and View-Updates

no code implementations13 Jun 2015 Babak Salimi, Leopoldo Bertossi

Causality has been recently introduced in databases, to model, characterize and possibly compute causes for query results (answers).

Cannot find the paper you are looking for? You can Submit a new open access paper.