Awa Dieng
Hi! I am a researcher at Google DeepMind, previously Google Brain. The overarching goal of my work is to build trustworthy AI systems that can be deployed safely. My current areas of interest are fairness, unlearning, generalization, and health, taking into account the social context in which models are used.
I am also the founder and co-organizer of the Algorithmic Fairness through the lens of <X> workshop series at NeurIPS, which advances the discussion of fairness in relation to other aspects of trustworthiness, such as interpretability, robustness, privacy, causality.
My previous research explored topics in causal inference including improving treatment effect estimation methods and studying their generalizability. I also investigated instance-based attribution techniques and causal approaches for interpretability.
See my publications page or my google scholar for an updated list of publications.
Email: awaydieng {at} gmail {dot} com
X / bluesky: @adoubleva
News
[Preprint] Check out our new preprint - The Nteasee study - detailing the landscape of AI in health in Africa from a fairness and equity angle.
[Talk] Excited to give an invited talk at the Deep Learning Indaba 2024
[Preprint] Check out our new preprint: Contextual Evaluation of Large Language Models for Classifying Tropical and Infectious Diseases
[Publication] Our paper - The Case for Globalizing Fairness: A Mixed Methods Study on Colonialism, AI, and Health in Africa - was accepted at EAAMO'24
[Publication] Our paper on Surfacing Health Equity Harms and Biases in Large Language Models has been published in Nature Medicine
[Talk] Excited to give an invited talk at the Symposium on Causation, Complexity, Cognition, and Representation for Responsible AI
[Service] Excited to organize a 5th edition of our workshop on Algorithmic Fairness at NeurIPS 2024 (details at Algorithmic Fairness through the lens of Metrics and Evaluation)
[Publication] Our paper on transportability of causal effects using RCT and observational data is now published in Statistical Science
[Service] The proceedings at PMLR for the Algorithmic Fairness through the lens of Causality and Privacy workshop is out!
[Service] I am Program Chair for the Montreal AI Symposium 2022. Looking forward to helping organize this great conference
[Research activity] I am leading a reading group on causal explainability at the Simons Institute cluster on Interpretable Machine Learning
Research activity] Honoured to be invited to participate in the Interpretable Machine Learning program at the Simons Institute for the Theory of Computing, UC Berkeley this summer