Journal: Entropy

Article Title: Unsupervised Embedding Learning for Large-Scale Heterogeneous Networks Based on Metapath Graph Sampling

doi: 10.3390/e25020297

Figure Lengend Snippet: Framework of the LHGI model.

Article Snippet: In this paper, we propose a large-scale heterogeneous network embedding learning model LHGI (Large-scale Heterogeneous Graph Infomax) based on metapath graph sampling technology.

Techniques:

Journal: Entropy

Article Title: Unsupervised Embedding Learning for Large-Scale Heterogeneous Networks Based on Metapath Graph Sampling

doi: 10.3390/e25020297

Figure Lengend Snippet: Classification performance of each model.

Article Snippet: In this paper, we propose a large-scale heterogeneous network embedding learning model LHGI (Large-scale Heterogeneous Graph Infomax) based on metapath graph sampling technology.

Techniques:

Journal: Entropy

Article Title: Unsupervised Embedding Learning for Large-Scale Heterogeneous Networks Based on Metapath Graph Sampling

doi: 10.3390/e25020297

Figure Lengend Snippet: Classification performance of node vectors learned by LHGI under different classifiers.

Article Snippet: In this paper, we propose a large-scale heterogeneous network embedding learning model LHGI (Large-scale Heterogeneous Graph Infomax) based on metapath graph sampling technology.

Techniques:

Journal: NAR Genomics and Bioinformatics

Article Title: Cancer drug sensitivity estimation using modular deep Graph Neural Networks

doi: 10.1093/nargab/lqae043

Figure Lengend Snippet: Ablation study: performance measures ± standard error of the mean. ‘ \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} $\checkmark$\end{document} ’ indicates included, ‘×’ indicates excluded model components; the first two rows are the complete CANDELA model with the two different pre-training stragies. Models marked ‘ † ’ are significantly worse than CANDELA using only one pre-training task. Models marked ‘*’ are significantly better (pairwise t -test, α = 0.05, corrected for multiple testing using Holm–Šídák). Bold values indicate the best configuration

Article Snippet: , 3D Infomax , \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} $\checkmark$\end{document} , \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} $\checkmark$\end{document} , Cross-attention , 0.0112 ± 0.0008 , 0.4339 ± 0.0070 † , 0.0269 ± 0.0061 †.

Techniques: