Urszula Chajewska

Microsoft (United States) — United States

Computer Science · Physical Sciences

9h-index769citations28works2.22yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Bayesian Modeling and Causal Inference(18), Explainable Artificial Intelligence (XAI)(6), Machine Learning and Data Classification(5), Neural Networks and Applications(3), Time Series Analysis and Forecasting(3)

Publications28 total

Interpretable machine learning leverages proteomics to improve cardiovascular disease risk prediction and biomarker identification
Communications Medicine·2025· 6 citedOpen Access
Federated Learning with Neural Graphical Models
Communications in computer and information science·2024
An Approach to Quantify Plans Robustness in Real-world Applications
2024Open Access
Methods for Recovering Conditional Independence Graphs: A Survey
Journal of Artificial Intelligence Research·2024· 1 citedOpen Access
Interpretable Machine Learning Leverages Proteomics to Improve Cardiovascular Disease Risk Prediction and Biomarker Identification
2024· 4 citedOpen Access
Neural Graph Revealers
Lecture notes in computer science·2023· 4 cited
Neural Graphical Models
Lecture notes in computer science·2023· 6 cited
Federated Learning with Neural Graphical Models
arXiv (Cornell University)·2023Open Access
Knowledge Propagation over Conditional Independence Graphs
arXiv (Cornell University)·2023· 1 citedOpen Access
Missing Values and Imputation in Healthcare Data: Can Interpretable Machine Learning Help?
arXiv (Cornell University)·2023· 5 citedOpen Access
Neural Graph Revealers
arXiv (Cornell University)·2023· 1 citedOpen Access
Methods for Recovering Conditional Independence Graphs: A Survey
arXiv (Cornell University)·2022· 3 citedOpen Access
Neural Graphical Models
arXiv (Cornell University)·2022· 1 citedOpen Access
uGLAD: Sparse graph recovery by optimizing deep unrolled networks
arXiv (Cornell University)·2022· 5 citedOpen Access
Discovering Distribution Shifts using Latent Space Representations
arXiv (Cornell University)·2022· 1 citedOpen Access
Factors associated with age of death in sudden unexpected infant death
Acta Paediatrica·2020· 11 citedOpen Access
Axiomatic Interpretability for Multiclass Additive Models
2019· 37 cited
Interpretability is Harder in the Multiclass Setting: Axiomatic Interpretability for Multiclass Additive Models.
arXiv (Cornell University)·2018· 3 citedOpen Access
Axiomatic Interpretability for Multiclass Additive Models
arXiv (Cornell University)·2018Open Access
Defining Explanation in Probabilistic Systems
arXiv (Cornell University)·2013· 61 citedOpen Access
page 1 of 2Next →

Frequent Co-authors

Harsh Shrivastava(11), Daphne Koller(4), Sarah Tan(4), Rich Caruana(4), Xuezhou Zhang(3), Paul Koch(3), Yin Lou(3), Robin Abraham(3), Héctor Climente-González(2), Min Oh(2), Roya Hosseini(2), Sudipto Mukherjee(2), Wei Gan(2), Matthew Traylor(2), Sile Hu(2), Ghazaleh Fatemifar(2), Paul Pangilinan Del Villar(2), Erik Vernet(2), Nils Koelling(2), Liang Du(2)