Adversarial attacks and defenses in images, graphs and text: A review
Deep neural networks (DNN) have achieved unprecedented success in numerous machine
learning tasks in various domains. However, the existence of adversarial examples raises …
learning tasks in various domains. However, the existence of adversarial examples raises …
Graph structure learning for robust graph neural networks
Graph Neural Networks (GNNs) are powerful tools in representation learning for graphs.
However, recent studies show that GNNs are vulnerable to carefully-crafted perturbations, …
However, recent studies show that GNNs are vulnerable to carefully-crafted perturbations, …
Graph neural networks for social recommendation
In recent years, Graph Neural Networks (GNNs), which can naturally integrate node information
and topological structure, have been demonstrated to be powerful in learning on graph …
and topological structure, have been demonstrated to be powerful in learning on graph …
Lead‐free perovskite photodetectors: progress, challenges, and opportunities
Y Zhang, Y Ma, Y Wang, X Zhang, C Zuo… - Advanced …, 2021 - Wiley Online Library
State‐of‐the‐art photodetectors which apply hybrid perovskite materials have emerged as
powerful candidates for next‐generation light sensing. Among them, lead‐based ones are the …
powerful candidates for next‐generation light sensing. Among them, lead‐based ones are the …
Calcium permeable-AMPA receptors and excitotoxicity in neurological disorders
C Guo, YY Ma - Frontiers in neural circuits, 2021 - frontiersin.org
Excitotoxicity is one of the primary mechanisms of cell loss in a variety of diseases of the
central and peripheral nervous systems. Other than the previously established signaling …
central and peripheral nervous systems. Other than the previously established signaling …
Traffic flow prediction via spatial temporal graph neural network
Traffic flow analysis, prediction and management are keystones for building smart cities in
the new era. With the help of deep neural networks and big traffic data, we can better …
the new era. With the help of deep neural networks and big traffic data, we can better …
Fitbit®: An accurate and reliable device for wireless physical activity tracking
…, MJ Chang, J Peacock, Y Ma… - International journal …, 2015 - pmc.ncbi.nlm.nih.gov
Although physicians recognize the importance of physical activity in the prevention and
maintenance of chronic diseases, 1 few incorporate physical activity counseling into routine …
maintenance of chronic diseases, 1 few incorporate physical activity counseling into routine …
Risk factors associated with clinical outcomes in 323 coronavirus disease 2019 (COVID-19) hospitalized patients in Wuhan, China
…, J Liu, C Shao, J Hao, C Wang, Y Ma… - Clinical infectious …, 2020 - academic.oup.com
Background With evidence of sustained transmission in more than 190 countries, coronavirus
disease 2019 (COVID-19) has been declared a global pandemic. Data are urgently …
disease 2019 (COVID-19) has been declared a global pandemic. Data are urgently …
Exaggerated inflammation, impaired host defense, and neuropathology in progranulin-deficient mice
Progranulin (PGRN) is a widely expressed protein involved in diverse biological processes.
Haploinsufficiency of PGRN in the human causes tau-negative, ubiquitin-positive …
Haploinsufficiency of PGRN in the human causes tau-negative, ubiquitin-positive …
Is homophily a necessity for graph neural networks?
Graph neural networks (GNNs) have shown great prowess in learning representations
suitable for numerous graph-based machine learning tasks. When applied to semi-supervised …
suitable for numerous graph-based machine learning tasks. When applied to semi-supervised …