Learning Performance Maximizing Ensembles with Explainability Guarantees

no code implementations • 20 Dec 2023 • Vincent Pisztora, Jia Li

In this paper we propose a method for the optimal allocation of observations between an intrinsically explainable glass box model and a black box model.

Epsilon Consistent Mixup: Structural Regularization with an Adaptive Consistency-Interpolation Tradeoff

no code implementations • 19 Apr 2021 • Vincent Pisztora, Yanglan Ou, Xiaolei Huang, Francesca Chiaromonte, Jia Li

In this paper we propose $\epsilon$-Consistent Mixup ($\epsilon$mu).

Semi-Supervised Cervical Dysplasia Classification With Learnable Graph Convolutional Network

no code implementations • 1 Apr 2020 • Yanglan Ou, Yuan Xue, Ye Yuan, Tao Xu, Vincent Pisztora, Jia Li, Xiaolei Huang

In this paper, we propose a novel and more flexible GCN model with a feature encoder that adaptively updates the adjacency matrix during learning and demonstrate that this model design leads to improved performance.

Classification General Classification