Results 1 to 10 of about 719 (136)

Evaluating explainability for graph neural networks [PDF]

Scientific Data, 2023
As explanations are increasingly used to understand the behavior of graph neural networks (GNNs), evaluating the quality and reliability of GNN explanations is crucial.
Chirag Agarwal, Owen Queen, Himabindu Lakkaraju, Marinka Zitnik   +3 more
doaj   +2 more sources

Attention-augmented and depthwise separable convolutional message passing for robust fraud detection in large-scale graphs [PDF]

Journal of Advanced Research
Introduction: Graph Neural Networks (GNNs) have shown great promise in fraud detection tasks on graph-structured data. However, they struggle with challenges such as label imbalance and the presence of heterophilic neighbours, which can obscure ...
Ijeoma A. Chikwendu, Xiaoling Zhang, Chiagoziem C. Ukwuoma, Chibueze D. Ukwuoma, Isaac Adjei-Mensah, Chinedu I. Otuka, Chukwuebuka Joseph Ejiyi, Yeong Hyeon Gu, Mugahed A. Al-antari   +8 more
doaj   +2 more sources

SS-AdaMoE: Spatio-Spectral Adaptive Mixture of Experts with Global Structural Priors for Graph Node Classification [PDF]

Entropy
Graph Neural Networks (GNNs) have emerged as the standard for learning representations from graph-structured data. While traditional architectures relying on message-passing mechanisms excel in homophilic settings, they essentially function as fixed low ...
Xilin Kang, Tianyue Yu, Letao Wang, Yutong Guo, Fengjun Zhang   +4 more
doaj   +2 more sources

CurvAGN: Curvature-based Adaptive Graph Neural Networks for Predicting Protein-Ligand Binding Affinity [PDF]

BMC Bioinformatics, 2023
Accurately predicting the binding affinity between proteins and ligands is crucial for drug discovery. Recent advances in graph neural networks (GNNs) have made significant progress in learning representations of protein-ligand complexes to estimate ...
Jianqiu Wu, Hongyang Chen, Minhao Cheng, Haoyi Xiong   +3 more
doaj   +2 more sources

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

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   +2 more sources

Graph Convolutional Networks Guided by Explicitly Estimated Homophily and Heterophily Degree

Applied Sciences, 2022
Graph convolutional networks (GCNs) have been successfully applied to learning tasks on graph-structured data. However, most traditional GCNs based on graph convolutions assume homophily in graphs, which leads to a poor performance when dealing with ...
Rui Zhang, Xin Li
doaj   +1 more source

Graph Anomaly Detection Algorithm Based on Multi-View Heterogeneity Resistant Network

Information
Graph anomaly detection (GAD) aims to identify nodes or edges that deviate from normal patterns. However, the presence of heterophilic edges in graphs leads to feature over-smoothing issues. To overcome this limitation, this paper proposes the multi-view
Yangrui Fan, Caixia Cui, Zhiqiang Wang, Hui Qi, Zhen Tian   +4 more
doaj   +1 more source

Spectral Filtering Using Periodic Autoregressive Moving Average Graph Neural Networks for Heterophilic Graphs

IEEE Access
The importance of Graph Neural Networks (GNNs) has increased over the years due to their ability to handle non-Euclidean data. Most of the existing research mainly focuses on spatial relationships using neighboring nodes to aggregate information, which ...
Baimyrza Kalmyrzayev, Hashim Ali, Muhammad Tahir Akhtar   +2 more
doaj   +1 more source

Preserving Global Information for Graph Clustering with Masked Autoencoders

Mathematics
Graph clustering aims to divide nodes into different clusters without labels and has attracted great attention due to the success of graph neural networks (GNNs).
Rui Chen
doaj   +1 more source

A Mutual Information-Based Framework for Enhancing Graph Neural Networks on Heterophily

IEEE Access
Graph Neural Networks (GNNs) have demonstrated strong capabilities in analyzing structured data, particularly under the assumption of homophily, where neighboring nodes tend to share similar attributes.
Gahee Kim, Seongjin Choi, Se-Young Yun
doaj   +1 more source