Célia W. AYAD

Office 1066

1 Rue Honoré d'Estienne d'Orves

91120 Palaiseau

I am Célia W. AYAD a PhD candidate, under the supervision of prof. Jesse Read, in the Data Science and Mining Team at the Laboratoire d’Informatique of École Polytechnique in France. Previously, I completed my MSc in Machine Learning for Data Sciences at Université Paris Cité.

My current research interests include: Machine Learning Explainability, Probabilistic Graphical Models, Uncertainty Quantification and Causality.

My academic CV can be accessed here.

news

Aug 1, 2023	Excited to present our paper Which Explanation Makes Sense? A Critical Evaluation of Local Explanations for Assessing Cervical Cancer Risk Factors at MLHC in NYC, USA.
Jan 1, 2023	Research collaboration under the supervision of Prof. Sonali Parbhoo at Imperial College London, UK.
Sep 1, 2022	Research visit under the supervision of Prof. Martino at URJC, Spain.
Aug 1, 2022	Attended OxML Summer School, Health Track at the university of oxford, UK.
Jul 1, 2022	Presented “Explainable Multi-output Model and Prediction” poster at IDA 2022.
Jun 1, 2021	Presented “Different Approaches towards Explainable Machine Learning” at WiDS Paris event.
Jan 1, 2021	Assisting Prof. Read in teaching Advanced Machine Learning and Autonomous Agents.
Aug 1, 2017	Participated in Preparing for Your Career Panel at the American University of Beirut, Lebanon.
Apr 1, 2014	Participated in Annual NYUAD International Hackathon for Social Good in the Arab World, UAE.

selected publications

ShapChains

Shapley chains: Extending Shapley values to Classifier chains

Célia Wafa Ayad, Thomas Bonnier, Benjamin Bosch, and 1 more author

Oct 2022

Abs Code

In spite of increased attention on explainable machine learning models, explaining multi-output predictions has not yet been extensively addressed. Methods that use Shapley values to attribute feature contributions to the decision making are one of the most popular approaches to explain local individual and global predictions. By considering each output separately in multi-output tasks, these methods fail to provide complete feature explanations. We propose Shapley chains to overcome this issue by including label interdependencies in the explanation design process. Shapley chains assign Shapley values as feature importance scores in multi-output classification using classifier chains, by separating the direct and indirect influence of these feature scores. Compared to existing methods, this approach allows to attribute a more complete feature contribution to the predictions of multi-output classification tasks. We provide a mechanism to distribute the hidden contributions of the outputs with respect to a given chaining order of these outputs. Moreover, we show how our approach can reveal indirect feature contributions missed by existing approaches. Shapley chains help to emphasize the real learning factors in multi-output applications and allows a better understanding of the flow of information through output interdependencies in synthetic and real-world datasets.
XAICancer

Which Explanation Makes Sense? A Critical Evaluation of Local Explanations for Assessing Cervical Cancer Risk Factors

Célia Wafa Ayad, Thomas Bonnier, Benjamin Bosch, and 2 more authors

Aug 2023

Abs Code

Cervical cancer is a life-threatening disease and one of the most prevalent types of cancer affecting women worldwide. Being able to adequately identify and assess factors that elevate risk of cervical cancer is crucial for early detection and treatment. Advances in machine learning have produced new methods for predicting cervical cancer risk, however their complex black-box behaviour remains a key barrier to their adoption in clinical practice. Recently, there has been substantial rise in the development of local explainability techniques aimed at breaking down a model’s predictions for particular instances in terms of, for example, meaningful concepts, important features, decision tree or rule-based logic, among others. While these techniques can help users better understand key factors driving a model’s decisions in some situations, they may not always be consistent or provide faithful predictions, particularly in applications with heterogeneous outcomes. In this paper, we present a critical analysis of several existing local interpretability methods for explaining risk factors associated with cervical cancer. Our goal is to help clinicians who use AI to better understand which types of explanations to use in particular contexts. We present a framework for studying the quality of different explanations for cervical cancer risk and contextualise how different explanations might be appropriate for different patient scenarios through an empirical analysis. Finally, we provide practical advice for practitioners as to how to use different types of explanations for assessing and determining key factors driving cervical cancer risk.