Results 71 to 80 of about 4,261,155 (305)
Graph Neural Networks (GNNs) have shown advantages in various graph-based applications. Most existing GNNs assume strong homophily of graph structure and apply permutation-invariant local aggregation of neighbors to learn a representation for each node. However, they fail to generalize to heterophilic graphs, where most neighboring nodes have different
Tianmeng Yang +5 more
openaire +3 more sources
Deep recurrent graph neural networks [PDF]
Graph Neural Networks (GNN) show good results in classification and regression on graphs, notwithstanding most GNN models use a limited depth. In fact, they are composed of only a few stacked graph convolutional layers.
Pasa L., Sperduti A., Navarin N.
core
Dual-channel deep graph convolutional neural networks
The dual-channel graph convolutional neural networks based on hybrid features jointly model the different features of networks, so that the features can learn each other and improve the performance of various subsequent machine learning tasks.
Zhonglin Ye +15 more
doaj +1 more source
Emerging experimental and computational methods for studying redox‐regulated structural transitions
Redox reactions can reshape proteins and alter how they behave in cells, with important consequences for health and disease. This review explores emerging experimental and computational approaches for discovering these redox‐sensitive protein switches, revealing their structural effects, and predicting their behavior, opening new opportunities to ...
Tasneem Rass +2 more
wiley +1 more source
Graph neural network driven traffic prediction technology:review and challenge
With the rapid development of Internet of things and artificial intelligence technology, accurate analysis and prediction of traffic data have become the primary target of intelligent transportations.In recent years, the method of traffic forecasting has
Yi ZHOU +5 more
doaj +2 more sources
Graph Neural Network: A Comprehensive Review on Non-Euclidean Space
This review provides a comprehensive overview of the state-of-the-art methods of graph-based networks from a deep learning perspective. Graph networks provide a generalized form to exploit non-euclidean space data.
Nurul A. Asif +11 more
doaj +1 more source
Path integral based convolution and pooling for graph neural networks [PDF]
Graph neural networks (GNNs) extends the functionality of traditional neural networks to graph-structured data. Similar to CNNs, an optimized design of graph convolution and pooling is key to success.
Lio P. +4 more
core
Translophagy—A potential link between autophagy impairment and translational errors
Neurodegenerative diseases are characterised by the accumulation of abnormal proteins and protein aggregates, but their origin often remains unknown. We propose that selective autophagy removes damaged protein‐making machinery, preventing errors during protein synthesis.
Mykola V. Korolchuk +11 more
wiley +1 more source
Multiresolution Reservoir Graph Neural Network
Graph neural networks are receiving increasing attention as state-of-the-art methods to process graph-structured data. However, similar to other neural networks, they tend to suffer from a high computational cost to perform training. Reservoir computing (
Pasa L. +5 more
core +1 more source
Prospecting the protein design landscape
This review outlines the current state of various protein design approaches. We discuss the current possibilities enabled by recently released tools, highlight future avenues to pursue in protein design, and underscore the crucial role of key databases and resources for successful protein design workflows.
Jakob R. Riccabona +4 more
wiley +1 more source

