7 citations · 17 across the 8 of their papers we have counts for
9 papers
Stress-Testing ML Pipelines with Adversarial Data Corruption
Jiongli Zhu, Geyang Xu, Felipe Lorenzi +2
Structured data-quality issues, such as missing values correlated with demographics, culturally biased labels, or systemic selection biases, routinely degrade the reliability of ma…
Causal DAG Summarization (Full Version)
Anna Zeng, Michael Cafarella, Batya Kenig +3
Causal inference aids researchers in discovering cause-and-effect relationships, leading to scientific insights. Accurate causal estimation requires identifying confounding variabl…
Learning from Uncertain Data: From Possible Worlds to Possible Models
Jiongli Zhu, Su Feng, Boris Glavic +1
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…
Consistent Range Approximation for Fair Predictive Modeling
Jiongli Zhu, Sainyam Galhotra, Nazanin Sabri +1
This paper proposes a novel framework for certifying the fairness of predictive models trained on biased data. It draws from query answering for incomplete and inconsistent databas…
On Explaining Confounding Bias
Brit Youngmann, Michael Cafarella, Yuval Moskovitch +1
When analyzing large datasets, analysts are often interested in the explanations for surprising or unexpected results produced by their queries. In this work, we focus on aggregate…
Combining Counterfactuals With Shapley Values To Explain Image Models
Aditya Lahiri, Kamran Alipour, Ehsan Adeli +1
With the widespread use of sophisticated machine learning models in sensitive applications, understanding their decision-making has become an essential task. Models trained on tabu…
Explaining Image Classifiers Using Contrastive Counterfactuals in Generative Latent Spaces
Kamran Alipour, Aditya Lahiri, Ehsan Adeli +2
Despite their high accuracies, modern complex image classifiers cannot be trusted for sensitive tasks due to their unknown decision-making process and potential biases. Counterfact…
Interpretable Data-Based Explanations for Fairness Debugging
Romila Pradhan, Jiongli Zhu, Boris Glavic +1
A wide variety of fairness metrics and eXplainable Artificial Intelligence (XAI) approaches have been proposed in the literature to identify bias in machine learning models that ar…
Through the Data Management Lens: Experimental Analysis and Evaluation of Fair Classification
Maliha Tashfia Islam, Anna Fariha, Alexandra Meliou +1
Classification, a heavily-studied data-driven machine learning task, drives an increasing number of prediction systems involving critical human decisions such as loan approval and…