Fergus Imrie
Postdoc, UCLA
imrie [AT] ucla.edu
About me
I am a postdoctoral scholar at the University of California, Los Angeles (UCLA) in the Department of Electrical and Computer Engineering, working with Mihaela van der Schaar. My research focuses on developing machine learning methods and techniques for healthcare and medicine.
Previously, I completed my DPhil (PhD) at the University of Oxford in the Department of Statistics in the Oxford Protein Informatics Group (OPIG), supervised by Charlotte Deane. My studentship was supported by an iCASE award with Exscientia, supervised by Anthony Bradley. My thesis explored deep learning approaches for pre-clinical drug discovery, with an emphasis on generative molecular design.
Recent News
- [2024/01] Two papers accepted at ICLR 2024 on causal sensitivity analysis [Paper] and data-centric AI [Paper].
- [2023/12] DC-Check, a checklist-style framework for data-centric AI, was published in IEEE Transactions on Artificial Intelligence [Paper]
- [2023/10] Our paper developing parsimonious risk scores for lung cancer was published in PLOS Medicine [Paper]
- [2023/09] Our paper on model evaluation with synthetic test data was accepted at NeurIPS 2023 [Paper]
- [2023/09] We welcomed >300 participants to the CCAIM AI and Machine Learning Summer School [Website]
- [2023/08] Our perspective on XAI in healthcare was published in Nature Machine Intelligence [Paper]
- [2023/06] AutoPrognsis 2.0, our AutoML framework for diagnostic and prognostic modeling, was published in PLOS Digital Health [Paper] [Software] [Website]
- [2023/04] Our paper on transportable structure learning was accepted at ICML 2023 [Paper]
- [2023/04] Our paper on molecular optimisation with curriculum learning and deep RL was published in Nature Machine Intelligence [Paper]
- [2023/01] Our paper on regularizing neural networks using neural attributions was accepted at ICLR 2023 [Paper]
- [2023/01] Three papers accepted at AISTATS 2023 on self-supervised conformal prediction [Paper], imputation in treatment effect estimation [Paper], and synthetic data for survival analysis [Paper]
- [2022/10] We have released AutoPrognsis 2.0, our AutoML framework for diagnostic and prognostic modeling [Paper] [Software] [Website]
- [2022/09] Our paper on composite feature selection was accepted at NeurIPS 2022 [Paper]
- [2022/05] Our paper on treatment effect estimation was accepted by ICML 2022 [Paper]
- [2022/02] I gave a tutorial on time series in healthcare at AAAI-22 [Video] [Website] [Slides]
- [2022/01] Our paper on self-supervised feature selection was accepted by ICLR 2022 [Paper]
- [2021/10] Our paper on molecular design with pharmacophoric constraints was published in Chemical Science [Paper]
- [2021/09] Two papers accepted to NeurIPS 2021 on interpretability [Paper] and understanding decision-making [Paper]
Publications
Most recent publications on Google Scholar.
‡ indicates equal contribution.
Dissecting Sample Hardness: A Fine-Grained Analysis of Hardness Characterization Methods for Data-Centric AI
Nabeel Seedat, Fergus Imrie, Mihaela van der Schaar
International Conference on Learning Representations (ICLR). 2024.
A Neural Framework for Generalized Causal Sensitivity Analysis
Dennis Frauen, Fergus Imrie, Alicia Curth, Valentyn Melnychuk, Stefan Feuerriegel, Mihaela van der Schaar
International Conference on Learning Representations (ICLR). 2024.
Navigating Data-Centric Artificial Intelligence with DC-Check: Advances, Challenges, and Opportunities
Nabeel Seedat, Fergus Imrie, Mihaela van der Schaar
IEEE Transactions on Artificial Intelligence. 2023.
Assessing eligibility for lung cancer screening using parsimonious ensemble machine learning models: A development and validation study
Thomas Callender, Fergus Imrie, Bogdan Cebere, Nora Pashayan, Neal Navani, Mihaela van der Schaar, Sam M Janes
PLOS Medicine. 2023.
Can you rely on your model evaluation? Improving model evaluation with synthetic test data
Nabeel Seedat‡, Boris van Breugel‡, Fergus Imrie, Mihaela van der Schaar
Neural Information Processing Systems (NeurIPS). 2023.
Multiple stakeholders drive diverse interpretability requirements for machine learning in healthcare
Fergus Imrie, Robert Davis, Mihaela van der Schaar
Nature Machine Intelligence. 2023.
AutoPrognosis 2.0: Democratizing Diagnostic and Prognostic Modeling in Healthcare with Automated Machine Learning
Fergus Imrie, Bogdan Cebere, Eoin F McKinney, Mihaela van der Schaar
PLOS Digital Health. 2023.
Differentiable and Transportable Structure Learning
Jeroen Berrevoets, Nabeel Seedat, Fergus Imrie, Mihaela van der Schaar
International Conference on Machine Learning (ICML). 2023.
Testing the Limits of SMILES-based De Novo Molecular Generation with Curriculum and Deep Reinforcement Learning
Maranga Mokaya, Fergus Imrie, Willem P van Hoorn, Aleksandra Kalisz, Anthony R Bradley, Charlotte M Deane
Nature Machine Intelligence. 2023.
TANGOS: Regularizing Tabular Neural Networks through Gradient Orthogonalization and Specialization
Alan Jeffares‡, Tennison Liu‡, Jonathan Crabbé, Fergus Imrie, Mihaela van der Schaar
International Conference on Learning Representations (ICLR). 2023.
Improving Adaptive Conformal Prediction Using Self-Supervised Learning
Nabeel Seedat‡, Alan Jeffares‡, Fergus Imrie, Mihaela van der Schaar
International Conference on Artificial Intelligence and Statistics (AISTATS). 2023.
To Impute or not to Impute? Missing Data in Treatment Effect Estimation
Jeroen Berrevoets, Fergus Imrie, Trent Kyono, James Jordon, Mihaela van der Schaar
International Conference on Artificial Intelligence and Statistics (AISTATS). 2023.
SurvivalGAN: Generating Time-to-Event Data for Survival Analysis
Alexander Norcliffe‡, Bogdan Cebere‡, Fergus Imrie, Pietro Lio, Mihaela van der Schaar
International Conference on Artificial Intelligence and Statistics (AISTATS). 2023.
Composite Feature Selection using Deep Ensembles
Fergus Imrie‡, Alexander Norcliffe‡, Pietro Lio, Mihaela van der Schaar
Neural Information Processing Systems (NeurIPS). 2022.
Continuous-Time Modeling of Counterfactual Outcomes Using Neural Controlled Differential Equations
Nabeel Seedat‡, Fergus Imrie‡, Alexis Bellot, Zhaozhi Qian, Mihaela van der Schaar
International Conference on Machine Learning (ICML). 2022.
Self-Supervision Enhanced Feature Selection with Correlated Gates
Changhee Lee‡, Fergus Imrie‡, Mihaela van der Schaar
International Conference on Learning Representations (ICLR). 2022. [Spotlight]
Explaining Latent Representations with a Corpus of Examples
Jonathan Crabbé, Zhaozhi Qian, Fergus Imrie, Mihaela van der Schaar
Neural Information Processing Systems (NeurIPS). 2021. [Spotlight]
Closing the loop in medical decision support by understanding clinical decision-making: A case study on organ transplantation
Yuchao Qin‡, Fergus Imrie‡, Alihan Hüyük, Daniel Jarrett, Alexander Gimson, Mihaela van der Schaar
Neural Information Processing Systems (NeurIPS). 2021.
Deep generative design with 3D pharmacophoric constraints
Fergus Imrie, Thomas E Hadfield, Anthony R Bradley, Charlotte M Deane
Chemical Science. 2021.
Generating property-matched decoy molecules using deep learning
Fergus Imrie, Anthony R Bradley, Charlotte M Deane
Bioinformatics. 2021.
Deep Generative Models for 3D Linker Design
Fergus Imrie, Anthony R Bradley, Mihaela van der Schaar, Charlotte M Deane
Journal of Chemical Information and Modeling. 2020.
Protein Family-Specific Models using Deep Neural Networks and Transfer Learning Improve Virtual Screening and Highlight the Need for More Data
Fergus Imrie, Anthony R Bradley, Mihaela van der Schaar, Charlotte M Deane
Journal of Chemical Information and Modeling. 2018.
Dissecting Sample Hardness: A Fine-Grained Analysis of Hardness Characterization Methods for Data-Centric AI
Nabeel Seedat, Fergus Imrie, Mihaela van der Schaar
International Conference on Learning Representations (ICLR). 2024.
A Neural Framework for Generalized Causal Sensitivity Analysis
Dennis Frauen, Fergus Imrie, Alicia Curth, Valentyn Melnychuk, Stefan Feuerriegel, Mihaela van der Schaar
International Conference on Learning Representations (ICLR). 2024.
Navigating Data-Centric Artificial Intelligence with DC-Check: Advances, Challenges, and Opportunities
Nabeel Seedat, Fergus Imrie, Mihaela van der Schaar
IEEE Transactions on Artificial Intelligence. 2023.
Redefining Digital Health Interfaces with Large Language Models
Fergus Imrie, Paulius Rauba, Mihaela van der Schaar
arXiv (Preprint). 2023.
Assessing eligibility for lung cancer screening using parsimonious ensemble machine learning models: A development and validation study
Thomas Callender, Fergus Imrie, Bogdan Cebere, Nora Pashayan, Neal Navani, Mihaela van der Schaar, Sam M Janes
PLOS Medicine. 2023.
Novel Preoperative Risk Stratification using Digital Phenotyping Applying a Scalable Machine Learning Approach
Pascal Laferriere-Lanlgois, Fergus Imrie, Marc-Andre Geraldo, Theodora Wingert, Nadia Lahrichi, Mihaela van der Schaar, Maxime Cannesson
Anesthesia & Analgesia. 2023.
Can you rely on your model evaluation? Improving model evaluation with synthetic test data
Nabeel Seedat‡, Boris van Breugel‡, Fergus Imrie, Mihaela van der Schaar
Neural Information Processing Systems (NeurIPS). 2023.
Multiple stakeholders drive diverse interpretability requirements for machine learning in healthcare
Fergus Imrie, Robert Davis, Mihaela van der Schaar
Nature Machine Intelligence. 2023.
AutoPrognosis 2.0: Democratizing Diagnostic and Prognostic Modeling in Healthcare with Automated Machine Learning
Fergus Imrie, Bogdan Cebere, Eoin F McKinney, Mihaela van der Schaar
PLOS Digital Health. 2023.
Differentiable and Transportable Structure Learning
Jeroen Berrevoets, Nabeel Seedat, Fergus Imrie, Mihaela van der Schaar
International Conference on Machine Learning (ICML). 2023.
Machine Learning with Requirements: A Manifesto
Eleonora Giunchiglia, Fergus Imrie, Mihaela van der Schaar, Thomas Lukasiewicz
arXiv (Preprint). 2023.
Testing the Limits of SMILES-based De Novo Molecular Generation with Curriculum and Deep Reinforcement Learning
Maranga Mokaya, Fergus Imrie, Willem P van Hoorn, Aleksandra Kalisz, Anthony R Bradley, Charlotte M Deane
Nature Machine Intelligence. 2023.
TANGOS: Regularizing Tabular Neural Networks through Gradient Orthogonalization and Specialization
Alan Jeffares‡, Tennison Liu‡, Jonathan Crabbé, Fergus Imrie, Mihaela van der Schaar
International Conference on Learning Representations (ICLR). 2023.
Improving Adaptive Conformal Prediction Using Self-Supervised Learning
Nabeel Seedat‡, Alan Jeffares‡, Fergus Imrie, Mihaela van der Schaar
International Conference on Artificial Intelligence and Statistics (AISTATS). 2023.
To Impute or not to Impute? Missing Data in Treatment Effect Estimation
Jeroen Berrevoets, Fergus Imrie, Trent Kyono, James Jordon, Mihaela van der Schaar
International Conference on Artificial Intelligence and Statistics (AISTATS). 2023.
SurvivalGAN: Generating Time-to-Event Data for Survival Analysis
Alexander Norcliffe‡, Bogdan Cebere‡, Fergus Imrie, Pietro Lio, Mihaela van der Schaar
International Conference on Artificial Intelligence and Statistics (AISTATS). 2023.
Composite Feature Selection using Deep Ensembles
Fergus Imrie‡, Alexander Norcliffe‡, Pietro Lio, Mihaela van der Schaar
Neural Information Processing Systems (NeurIPS). 2022.
Continuous-Time Modeling of Counterfactual Outcomes Using Neural Controlled Differential Equations
Nabeel Seedat‡, Fergus Imrie‡, Alexis Bellot, Zhaozhi Qian, Mihaela van der Schaar
International Conference on Machine Learning (ICML). 2022.
Incorporating Target-Specific Pharmacophoric Information into Deep Generative Models for Fragment Elaboration
Thomas E Hadfield, Fergus Imrie, Andy Merritt, Kristian Birchall, Charlotte M Deane
Journal of Chemical Information and Modeling. 2022.
Self-Supervision Enhanced Feature Selection with Correlated Gates
Changhee Lee‡, Fergus Imrie‡, Mihaela van der Schaar
International Conference on Learning Representations (ICLR). 2022. [Spotlight]
Explaining Latent Representations with a Corpus of Examples
Jonathan Crabbé, Zhaozhi Qian, Fergus Imrie, Mihaela van der Schaar
Neural Information Processing Systems (NeurIPS). 2021. [Spotlight]
Closing the loop in medical decision support by understanding clinical decision-making: A case study on organ transplantation
Yuchao Qin‡, Fergus Imrie‡, Alihan Hüyük, Daniel Jarrett, Alexander Gimson, Mihaela van der Schaar
Neural Information Processing Systems (NeurIPS). 2021.
Deep generative design with 3D pharmacophoric constraints
Fergus Imrie, Thomas E Hadfield, Anthony R Bradley, Charlotte M Deane
Chemical Science. 2021.
Generating property-matched decoy molecules using deep learning
Fergus Imrie, Anthony R Bradley, Charlotte M Deane
Bioinformatics. 2021.
Virtual Screening with Convolutional Neural Networks
Fergus Imrie, Anthony R Bradley, Charlotte M Deane
Artificial Intelligence in Drug Discovery (Book Chapter). 2020.
Deep Generative Models for 3D Linker Design
Fergus Imrie, Anthony R Bradley, Mihaela van der Schaar, Charlotte M Deane
Journal of Chemical Information and Modeling. 2020.
Protein Family-Specific Models using Deep Neural Networks and Transfer Learning Improve Virtual Screening and Highlight the Need for More Data
Fergus Imrie, Anthony R Bradley, Mihaela van der Schaar, Charlotte M Deane
Journal of Chemical Information and Modeling. 2018.
Redefining Digital Health Interfaces with Large Language Models
Fergus Imrie, Paulius Rauba, Mihaela van der Schaar
arXiv (Preprint). 2023.
Machine Learning with Requirements: A Manifesto
Eleonora Giunchiglia, Fergus Imrie, Mihaela van der Schaar, Thomas Lukasiewicz
arXiv (Preprint). 2023.