371 citations · 1.3k across the 68 of their papers we have counts for
15 papers · 1 filter
Wasserstein Contrastive Representation Distillation
Liqun Chen, Dong Wang, Zhe Gan +3
The primary goal of knowledge distillation (KD) is to encapsulate the information of a model learned from a teacher network into a student network, with the latter being more compa…
Proactive Pseudo-Intervention: Causally Informed Contrastive Learning For Interpretable Vision Models
Dong Wang, Yuewei Yang, Chenyang Tao +5
Deep neural networks excel at comprehending complex visual signals, delivering on par or even superior performance to that of human experts. However, ad-hoc visual explanations of…
Supercharging Imbalanced Data Learning With Energy-based Contrastive Representation Transfer
Zidi Xiu, Junya Chen, Ricardo Henao +3
Dealing with severe class imbalance poses a major challenge for real-world applications, especially when the accurate classification and generalization of minority classes is of pr…
Estimating Total Correlation with Mutual Information Estimators
Ke Bai, Pengyu Cheng, Weituo Hao +2
Total correlation (TC) is a fundamental concept in information theory that measures statistical dependency among multiple random variables. Recently, TC has shown noticeable effect…
Counterfactual Representation Learning with Balancing Weights
Serge Assaad, Shuxi Zeng, Chenyang Tao +5
A key to causal inference with observational data is achieving balance in predictive features associated with each treatment type. Recent literature has explored representation lea…
Variational Disentanglement for Rare Event Modeling
Zidi Xiu, Chenyang Tao, Michael Gao +3
Combining the increasing availability and abundance of healthcare data and the current advances in machine learning methods have created renewed opportunities to improve clinical d…
Weakly supervised cross-domain alignment with optimal transport
Siyang Yuan, Ke Bai, Liqun Chen +6
Cross-domain alignment between image objects and text sequences is key to many visual-language tasks, and it poses a fundamental challenge to both computer vision and natural langu…
Adaptive multi-channel event segmentation and feature extraction for monitoring health outcomes
Xichen She, Yaya Zhai, Ricardo Henao +5
: To develop a multi-channel device event segmentation and feature extraction algorithm that is robust to changes in data distribution. : We i…
Students Need More Attention: BERT-based AttentionModel for Small Data with Application to AutomaticPatient Message Triage
Shijing Si, Rui Wang, Jedrek Wosik +5
Small and imbalanced datasets commonly seen in healthcare represent a challenge when training classifiers based on deep learning models. So motivated, we propose a novel framework…
Enabling Counterfactual Survival Analysis with Balanced Representations
Paidamoyo Chapfuwa, Serge Assaad, Shuxi Zeng +3
Balanced representation learning methods have been applied successfully to counterfactual inference from observational data. However, approaches that account for survival outcomes…
Neural Conditional Event Time Models
Matthew Engelhard, Samuel Berchuck, Joshua D'Arcy +1
Event time models predict occurrence times of an event of interest based on known features. Recent work has demonstrated that neural networks achieve state-of-the-art event time pr…
Variational Learning of Individual Survival Distributions
Zidi Xiu, Chenyang Tao, Benjamin A. Goldstein +1
The abundance of modern health data provides many opportunities for the use of machine learning techniques to build better statistical models to improve clinical decision making. P…
Survival Cluster Analysis
Paidamoyo Chapfuwa, Chunyuan Li, Nikhil Mehta +2
Conventional survival analysis approaches estimate risk scores or individualized time-to-event distributions conditioned on covariates. In practice, there is often great population…
Machine-Learning-Based Multiple Abnormality Prediction with Large-Scale Chest Computed Tomography Volumes
Rachel Lea Draelos, David Dov, Maciej A. Mazurowski +4
Machine learning models for radiology benefit from large-scale data sets with high quality labels for abnormalities. We curated and analyzed a chest computed tomography (CT) data s…
Learning Autoencoders with Relational Regularization
Hongteng Xu, Dixin Luo, Ricardo Henao +2
A new algorithmic framework is proposed for learning autoencoders of data distributions. We minimize the discrepancy between the model and target distributions, with a \emph{relati…