Out-of-distribution (OOD) detection is crucial to modern deep learning
a...
As a powerful Bayesian non-parameterized algorithm, the Gaussian process...
The theoretical analysis of multi-class classification has proved that t...
Transfer learning where the behavior of extracting transferable knowledg...
Causal effect estimation for dynamic treatment regimes (DTRs) contribute...
Traditional supervised learning aims to train a classifier in the closed...
Many methods have been proposed to detect concept drift, i.e., the chang...
By leveraging experience from previous tasks, meta-learning algorithms c...
Unsupervised domain adaptation (UDA) aims to train a target classifier w...
In data streams, the data distribution of arriving observations at diffe...
In unsupervised domain adaptation (UDA), a classifier for the target dom...
In unsupervised domain adaptation (UDA), classifiers for the target doma...
In the unsupervised open set domain adaptation (UOSDA), the target domai...
Concept drift refers to changes in the distribution of underlying data a...
Concept drift describes unforeseeable changes in the underlying distribu...
We propose a class of kernel-based two-sample tests, which aim to determ...
The purpose of network representation is to learn a set of latent featur...
Unsupervised domain adaptation for classification tasks has achieved gre...
In unsupervised domain adaptation (UDA), classifiers for the target doma...
Unsupervised domain adaptation (UDA) trains with clean labeled data in s...
This paper uses the weather forecasting as an application background to
...
The cooperative hierarchical structure is a common and significant data
...
Traditional Relational Topic Models provide a way to discover the hidden...
Incorporating the side information of text corpus, i.e., authors, time
s...