Results 71 to 80 of about 1,903,201 (339)

Thermodynamics-consistent graph neural networks

Chemical Science
We propose excess Gibbs free energy graph neural networks (GE-GNNs) for predicting composition-dependent activity coefficients of binary mixtures.
Jan G. Rittig, Alexander Mitsos
openalex   +7 more sources

k-Nearest Neighbor Learning with Graph Neural Networks

Mathematics, 2021
k-nearest neighbor (kNN) is a widely used learning algorithm for supervised learning tasks. In practice, the main challenge when using kNN is its high sensitivity to its hyperparameter setting, including the number of nearest neighbors k, the distance ...
Seokho Kang
doaj   +1 more source

Cascade2vec: Learning Dynamic Cascade Representation by Recurrent Graph Neural Networks

IEEE Access, 2019
An information dissemination network (i.e., a cascade) with a dynamic graph structure is formed when a novel idea or message spreads from person to person.
Zhenhua Huang, Zhenyu Wang, Rui Zhang
doaj   +1 more source

Time after time – circadian clocks through the lens of oscillator theory

FEBS Letters, EarlyView.
Oscillator theory bridges physics and circadian biology. Damped oscillators require external drivers, while limit cycles emerge from delayed feedback and nonlinearities. Coupling enables tissue‐level coherence, and entrainment aligns internal clocks with environmental cues.
Marta del Olmo, Carolin Ector, Hanspeter Herzel   +2 more
wiley   +1 more source

On Sampling Strategies for Neural Network-based Collaborative Filtering

, 2017
Recent advances in neural networks have inspired people to design hybrid recommendation algorithms that can incorporate both (1) user-item interaction information and (2) content information including image, audio, and text.
Bordes Antoine, Chen Tianqi, Chen Ting, Collobert Ronan, den Oord Aaron Van, Gopalan Prem K, Kingma Diederik, Krizhevsky Alex, Lin Xiao, Mikolov T, Reddi Sashank J, Rendle Steffen, Salakhutdinov Ruslan, Zhang Xiang, Zhao Peilin, Zheng Yin   +15 more
core   +1 more source

Torsion Graph Neural Networks

IEEE Transactions on Pattern Analysis and Machine Intelligence
Geometric deep learning (GDL) models have demonstrated a great potential for the analysis of non-Euclidian data. They are developed to incorporate the geometric and topological information of non-Euclidian data into the end-to-end deep learning architectures. Motivated by the recent success of discrete Ricci curvature in graph neural network (GNNs), we
Cong Shen, Xiang Liu, Jiawei Luo, Kelin Xia   +3 more
openaire   +3 more sources

Liquid biopsy epigenetics: establishing a molecular profile based on cell‐free DNA

Molecular Oncology, EarlyView.
Cell‐free DNA (cfDNA) fragments in plasma from cancer patients carry epigenetic signatures reflecting their cells of origin. These epigenetic features include DNA methylation, nucleosome modifications, and variations in fragmentation. This review describes the biological properties of each feature and explores optimal strategies for harnessing cfDNA ...
Christoffer Trier Maansson, Anders Lade Nielsen, Boe Sandahl Sorensen   +2 more
wiley   +1 more source

Graphs, Convolutions, and Neural Networks: From Graph Filters to Graph Neural Networks

IEEE Signal Processing Magazine, 2020
Signal Processing ...
Gama, F. (author), Isufi, E. (author), Leus, G.J.T. (author), Ribeiro, Alejandro (author)   +3 more
openaire   +6 more sources

Research on few-shot text classification techniques based on text-level-graph neural networks [PDF]

Journal of Hebei University of Science and Technology
In order to solve the problem of poor accuracy of text classification in text graph neural network with small samples, a text level graph neural network-prototypical (LGNN-Proto) was designed.
Xiangcheng AN, Baozhu LIU, Jingwei GAN
doaj   +1 more source

Graph Neural Network for Traffic Flow Situation Prediction

Jisuanji kexue yu tansuo, 2021
Road network structure integrated traffic flow situation prediction is a highly nonlinear and complexly spatial-temporal dynamic correlation time-series data prediction problem. However, traditional traffic flow situation forecasting methods cannot model
JIANG Shan, DING Zhiming, XU Xinrun, YAN Jin
doaj   +1 more source