Machine learning (ML) research has generally focused on models, while th...
Interpretability is becoming an active research topic as machine learnin...
Annotating the right set of data amongst all available data points is a ...
The reliability of machine learning models can be compromised when train...
Mixup is a popular data augmentation technique based on taking convex
co...
Data augmentation by incorporating cheap unlabeled data from multiple do...
Shapley value is a classic notion from game theory, historically used to...
We develop Neuron Shapley as a new framework to quantify the contributio...
Despite the recent success in applying supervised deep learning to medic...
A fancy learning algorithm A outperforms a baseline method B when they
a...
As data becomes the fuel driving technological and economic growth, a
fu...
Interpretability has become an important topic of research as more machi...
An important problem in machine learning and statistics is to identify
f...
Machine learning predictors are successfully deployed in applications ra...
In order for machine learning to be deployed and trusted in many
applica...