Heterophilic graphs - Open Access .click

Results 21 to 30 of about 415,143 (70)

Stability-Optimized Graph Convolutional Network: A Novel Propagation Rule with Constraints Derived from ODEs

Mathematics
The node representation learning capability of Graph Convolutional Networks (GCNs) is fundamentally constrained by dynamic instability during feature propagation, yet existing research lacks systematic theoretical analysis of stability control mechanisms.
Liping Chen, Hongji Zhu, Shuguang Han
doaj +1 more source

SETTA: Parameter-Free Test-Time Adaptation for Graph Neural Networks via Spectral-Energy-Guided Semantic Refinement

Big Data and Cognitive Computing
Node classification is a central graph data mining task, yet repeated message passing can over-smooth representations and degrade frozen graph neural network (GNN) predictions after deployment.
Dongyang Yu, Xia Cui, Rong Xiao
doaj +1 more source

Inferred global dense residue transition graphs from primary structure sequences enable protein interaction prediction via directed graph convolutional neural networks

Frontiers in Bioinformatics
IntroductionAccurate prediction of protein-protein interactions (PPIs) is crucial for understanding cellular functions and advancing the development of drugs.
Islam Akef Ebeid, Haoteng Tang, Pengfei Gu +2 more
doaj +1 more source

Fractional Variational Graph Autoencoders for Enhancing Non-Local Representation Learning on Graphs

Information
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

Learning Resilient Graph Structures in Heterophilic Settings [PDF]

Graphs provide a fundamental way to model relationships between entities and are central to numerous machine learning tasks. Standard graph-based methods often assume the provided graph structure is both accurate and complete.

core +4 more sources

Minimum Cycle Base of Graphs Identified by Two Planar Graphs [PDF]

, 2007
In this paper, we study the minimum cycle base of the planar graphs obtained from two 2-connected planar graphs by identifying an edge (or a cycle) of one graph with the corresponding edge (or cycle) of another, related with map geometries, i.e ...
Han, Ren, Dengju, Ma
core +1 more source

Uncertainty Estimation for Heterophilic Graphs Through the Lens of Information Theory [PDF]

While uncertainty estimation for graphs recently gained traction, most methods rely on homophily and deteriorate in heterophilic settings. We address this by analyzing message passing neural networks from an information-theoretic perspec tive and ...

core +1 more source

Plick Graphs with Crossing Number 1 [PDF]

, 2011
In this paper, we deduce a necessary and sufficient condition for graphs whose plick graphs have crossing number 1. We also obtain a necessary and sufficient condition for plick graphs to have crossing number 1 in terms of forbidden ...
Basavanagoud, B., Kulli, V.R.
core +1 more source

Mitigating Oversmoothing Through Reverse Process of GNNs for Heterophilic Graphs [PDF]

Graph Neural Network (GNN) resembles the diffusion process, leading to the over-smoothing of learned representations when stacking many layers. Hence, the reverse process of message passing can produce the distinguishable node representations by ...
Kim, Dongwoo, Heo, Jaeseung, Park, MoonJeong +2 more
core +1 more source

Refining Latent Homophilic Structures over Heterophilic Graphs for Robust Graph Convolution Networks

Graph convolution networks (GCNs) are extensively utilized in various graph tasks to mine knowledge from spatial data. Our study marks the pioneering attempt to quantitatively investigate the GCN robustness over omnipresent heterophilic graphs for node ...
Cui, Qimei +8 more
core +1 more source

graph neural networks
node classification