1.5k citations · 1.6k across the 41 of their papers we have counts for
7 papers · 1 filter
Contextual Learning for Anomaly Detection in Tabular Data
Spencer King, Zhilu Zhang, Ruofan Yu +3
Anomaly detection is critical in domains such as cybersecurity and finance, especially when working with large-scale tabular data. Yet, unsupervised anomaly detection-where no labe…
Ex uno plures: Splitting One Model into an Ensemble of Subnetworks
Zhilu Zhang, Vianne R. Gao, Mert R. Sabuncu
Monte Carlo (MC) dropout is a simple and efficient ensembling method that can improve the accuracy and confidence calibration of high-capacity deep neural network models. However,…
Self-Distillation as Instance-Specific Label Smoothing
Zhilu Zhang, Mert R. Sabuncu
It has been recently demonstrated that multi-generational self-distillation can improve generalization. Despite this intriguing observation, reasons for the enhancement remain poor…
Two-Dimensional Semi-Nonnegative Matrix Factorization for Clustering
Chong Peng, Zhilu Zhang, Zhao Kang +2
In this paper, we propose a new Semi-Nonnegative Matrix Factorization method for 2-dimensional (2D) data, named TS-NMF. It overcomes the drawback of existing methods that seriously…
Nonnegative Matrix Factorization with Local Similarity Learning
Chong Peng, Zhao Kang, Chenglizhao Chen +1
Existing nonnegative matrix factorization methods focus on learning global structure of the data to construct basis and coefficient matrices, which ignores the local structure that…
Confidence Calibration for Convolutional Neural Networks Using Structured Dropout
Zhilu Zhang, Adrian V. Dalca, Mert R. Sabuncu
In classification applications, we often want probabilistic predictions to reflect confidence or uncertainty. Dropout, a commonly used training technique, has recently been linked…
Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels
Zhilu Zhang, Mert R. Sabuncu
Deep neural networks (DNNs) have achieved tremendous success in a variety of applications across many disciplines. Yet, their superior performance comes with the expensive cost of…