We introduce a novel class of sample-based explanations we term
high-dim...
The eXtreme Multi-label Classification (XMC) problem seeks to find relev...
Uncertainty quantification is one of the most crucial tasks to obtain
tr...
Extreme multi-label classification (XMC) is a popular framework for solv...
Entropy regularized Markov decision processes have been widely used in
r...
The eXtreme Multi-label text Classification (XMC) problem concerns findi...
Learning on graphs has attracted significant attention in the learning
c...
Extreme multi-label text classification (XMC) seeks to find relevant lab...
Partition-based methods are increasingly-used in extreme multi-label
cla...
We consider the problem of semantic matching in product search: given a
...
Tree-based models underpin many modern semantic search engines and
recom...
Many challenging problems in modern applications amount to finding relev...
Extreme multi-label classification (XMC) is the problem of finding the
r...
We introduce a new way of learning to encode position information for
no...
The architecture of Transformer is based entirely on self-attention, and...
In this paper, we consider recommender systems with side information in ...
Forecasting high-dimensional time series plays a crucial role in many
ap...
Deep neural networks have yielded superior performance in many applicati...
Extreme multi-label classification (XMC) aims to assign to an instance t...
Word embedding is a key component in many downstream applications in
pro...
We propose extreme stochastic variational inference (ESVI), an asynchron...
High-dimensional time series prediction is needed in applications as div...