Interpreting time series models is uniquely challenging because it requi...
The transfer of models trained on labeled datasets in a source domain to...
As post hoc explanations are increasingly used to understand the behavio...
While several types of post hoc explanation methods (e.g., feature
attri...
Pre-training on time series poses a unique challenge due to the potentia...
Objective: Disease knowledge graphs are a way to connect, organize, and
...
As attribution-based explanation methods are increasingly used to establ...
Human space exploration beyond low Earth orbit will involve missions of
...
Space biology research aims to understand fundamental effects of spacefl...
In many domains, including healthcare, biology, and climate science, tim...
As Graph Neural Networks (GNNs) are increasingly employed in real-world
...
Spatial context is central to understanding health and disease. Yet refe...
With the remarkable success of representation learning in providing powe...
Language model pre-training (LMPT) has achieved remarkable results in na...
As the representations output by Graph Neural Networks (GNNs) are
increa...
Machine Learning (ML) models typically require large-scale, balanced tra...
The efficacy of a drug depends on its binding affinity to the therapeuti...
Deep learning methods for graphs achieve remarkable performance on many
...
Deep learning methods for graphs achieve remarkable performance on many
...
Prevailing methods for graphs require abundant label and edge informatio...
We present the Open Graph Benchmark (OGB), a diverse set of challenging ...
Molecular interaction networks are powerful resources for the discovery....
The COVID-19 pandemic demands the rapid identification of drug-repurpusi...
There is a need of ensuring machine learning models that are interpretab...
Many applications of machine learning in science and medicine, including...
Graph Neural Networks (GNNs) are a powerful tool for machine learning on...
NIMFA is an open-source Python library that provides a unified interface...
New technologies have enabled the investigation of biology and human hea...
Learning vector embeddings of complex networks is a powerful approach us...
Networks are ubiquitous in biology where they encode connectivity patter...
Uncovering modular structure in networks is fundamental for advancing th...
The use of multiple drugs, termed polypharmacy, is common to treat patie...
Motivation: Biomedical named entity recognition (BioNER) is the most
fun...
Nodes residing in different parts of a graph can have similar structural...
Motivation: The rapid growth of diverse biological data allows us to con...
Motivation: Understanding functions of proteins in specific human tissue...
For most problems in science and engineering we can obtain data sets tha...