5 papers
Jigsaw Regularization in Whole-Slide Image Classification
So Won Jeong, Veronika Ročková
Computational pathology involves the digitization of stained tissues into whole-slide images (WSIs) that contain billions of pixels arranged as contiguous patches. Statistical anal…
SpeedCP: Fast Kernel-based Conditional Conformal Prediction
Yating Liu, Yeo Jin Jung, Zixuan Wu +2
Conformal prediction provides distribution-free prediction sets with finite-sample conditional guarantees. We build upon the RKHS-based framework of Gibbs et al. (2023), which leve…
Filtering with Confidence: When Data Augmentation Meets Conformal Prediction
Zixuan Wu, So Won Jeong, Yating Liu +2
With promising empirical performance across a wide range of applications, synthetic data augmentation appears a viable solution to data scarcity and the demands of increasingly dat…
LOBSTUR: A Local Bootstrap Framework for Tuning Unsupervised Representations in Graph Neural Networks
So Won Jeong, Claire Donnat
Graph Neural Networks (GNNs) are increasingly used in conjunction with unsupervised learning techniques to learn powerful node representations, but their deployment is hindered by…
Tuning the Geometry of Graph Neural Networks
Sowon Jeong, Claire Donnat
By recursively summing node features over entire neighborhoods, spatial graph convolution operators have been heralded as key to the success of Graph Neural Networks (GNNs). Yet, d…