no code implementations • 21 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.
no code implementations • 17 Mar 2024 • Seyedeh Baharan Khatami, Harsh Parikh, Haowei Chen, Sudeepa Roy, Babak Salimi
Our paper addresses the challenge of inferring causal effects in social network data, characterized by complex interdependencies among individuals resulting in challenges such as non-independence of units, interference (where a unit's outcome is affected by neighbors' treatments), and introduction of additional confounding factors from neighboring units.
no code implementations • 4 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.
1 code implementation • 21 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.
no code implementations • 14 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.
no code implementations • 10 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.
no code implementations • 17 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
no code implementations • 22 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.
1 code implementation • 18 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.
no code implementations • 7 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.
no code implementations • 20 Aug 2019 • Babak Salimi, Bill Howe, Dan Suciu
Fairness is increasingly recognized as a critical component of machine learning systems.
no code implementations • 21 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.
no code implementations • 8 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.
no code implementations • 6 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.
no code implementations • 12 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.
no code implementations • 20 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.
no code implementations • 1 Jul 2015 • Leopoldo Bertossi, Babak Salimi
In this work we establish and investigate connections between causes for query answers in databases, database repairs wrt.
no code implementations • 13 Jun 2015 • Babak Salimi, Leopoldo Bertossi
Causality has been recently introduced in databases, to model, characterize and possibly compute causes for query results (answers).