most citedSurvivalGAN: Generating Time-to-Event Data for Survival Analysis

5 citations · 14 across the 6 of their papers we have counts for

collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2024

You can't handle the (dirty) truth: Data-centric insights improve pseudo-labeling

Nabeel Seedat, Nicolas Huynh, Fergus Imrie +1

Pseudo-labeling is a popular semi-supervised learning technique to leverage unlabeled data when labeled samples are scarce. The generation and selection of pseudo-labels heavily re…

cs.LG2024

Dissecting Sample Hardness: A Fine-Grained Analysis of Hardness Characterization Methods for Data-Centric AI

Nabeel Seedat, Fergus Imrie, Mihaela van der Schaar

Characterizing samples that are difficult to learn from is crucial to developing highly performant ML models. This has led to numerous Hardness Characterization Methods (HCMs) that…

cs.LG20235 cited

Can You Rely on Your Model Evaluation? Improving Model Evaluation with Synthetic Test Data

Boris van Breugel, Nabeel Seedat, Fergus Imrie +1

Evaluating the performance of machine learning models on diverse and underrepresented subgroups is essential for ensuring fairness and reliability in real-world applications. Howev…

cs.LG20233 cited

TANGOS: Regularizing Tabular Neural Networks through Gradient Orthogonalization and Specialization

Alan Jeffares, Tennison Liu, Jonathan Crabbé +2

Despite their success with unstructured data, deep neural networks are not yet a panacea for structured tabular data. In the tabular domain, their efficiency crucially relies on va…

cs.LG20235 cited

SurvivalGAN: Generating Time-to-Event Data for Survival Analysis

Alexander Norcliffe, Bogdan Cebere, Fergus Imrie +2

Synthetic data is becoming an increasingly promising technology, and successful applications can improve privacy, fairness, and data democratization. While there are many methods f…

cs.LG20231 cited

Improving Adaptive Conformal Prediction Using Self-Supervised Learning

Nabeel Seedat, Alan Jeffares, Fergus Imrie +1

Conformal prediction is a powerful distribution-free tool for uncertainty quantification, establishing valid prediction intervals with finite-sample guarantees. To produce valid in…