Results 41 to 50 of about 719 (136)
Fractional Variational Graph Autoencoders for Enhancing Non-Local Representation Learning on Graphs
While Graph Autoencoders (GAEs) have become a standard for unsupervised representation learning, their reliance on integer-order convolutions inherently restricts information propagation to immediate local neighborhoods.
Mohamed Ilyas El Harrak +5 more
doaj +1 more source
The Hunt for HLA‐DQ Allogeneic Eplets Is Not Over: Four New Ones, Including a Cross‐Chain Eplet
ABSTRACT The target of an anti‐HLA antibody is an epitope on the surface of the antigen, and in particular the polymorphic eplet of its core, which contains one or a few polymorphic residues accessible to the molecule surface. The HLA Eplet Registry database references more than 550 HLA eplets thus deduced from AA sequence alignments.
Magali Devriese +10 more
wiley +1 more source
THeGCN: Temporal Heterophilic Graph Convolutional Network
Graph Neural Networks (GNNs) have exhibited remarkable efficacy in diverse graph learning tasks, particularly on static homophilic graphs. Recent attention has pivoted towards more intricate structures, encompassing (1) static heterophilic graphs encountering the edge heterophily issue in the spatial domain and (2) event-based continuous graphs in the ...
Yan, Yuchen +8 more
openaire +2 more sources
The present study sought to investigate the protective effects of epigallocatechin‐3‐gallate (EGCG) on hydrogen peroxide‐induced oxidative stress, inflammation, and apoptosis, and related mechanisms. The test showed that EGCG could improve the antioxidant function of bovine mammary epithelial cells by activating the Nrf2 and inhibiting the p38 mitogen ...
Xuehu Ma +6 more
wiley +1 more source
Beyond Homophily: Community Search on Heterophilic Graphs
Community search aims to identify a refined set of nodes that are most relevant to a given query, supporting tasks ranging from fraud detection to recommendation. Unlike homophilic graphs, many real-world networks are heterophilic, where edges predominantly connect dissimilar nodes.
Qing Sima 0001 +2 more
openaire +2 more sources
Learning Laplacian Positional Encodings for Heterophilous Graphs
AISTATS 2025; version with full ...
Ito, M. +4 more
openaire +4 more sources
Data‐efficient graph learning: Problems, progress, and prospects
Abstract Graph‐structured data, ranging from social networks to financial transaction networks, from citation networks to gene regulatory networks, have been widely used for modeling a myriad of real‐world systems. As a prevailing model architecture to model graph‐structured data, graph neural networks (GNNs) have drawn much attention in both academic ...
Kaize Ding +3 more
wiley +1 more source
Evolution of CEACAM pathogen decoy receptors in primates
In humans, pathogen binding to the inhibitory receptor CEACAM1 on leukocytes allows immune escape while engagement of the neutrophil‐specific endocytic CEACAM3 decoy receptor enables destruction. Easily shed GPI‐linked epithelial CEACAM5 and CEACAM6 might act as soluble or extracellular vesicle‐bound decoy receptors.
Wolfgang Zimmermann, Robert Kammerer
wiley +1 more source
Six dimensions of online climate change polarization. Abstract Online climate change polarization has increasingly received academic interest over time. Online media facilitate and accelerate processes of climate change polarization. Yet, throughout the years, online climate change polarization became a fuzzy concept, holding different meanings in ...
Christel W. van Eck
wiley +1 more source
Self‐supervised multi‐view clustering in computer vision: A survey
The self‐supervised learning problem presents a significant challenge within the realm of MVC, and its investigation holds paramount importance for practical applications. The authors include commonly employed self‐supervised MVC datasets and related problems, offering insights from both image and video perspectives.
Jiatai Wang +5 more
wiley +1 more source

