Results 11 to 20 of about 415,143 (70)

Link Prediction on Heterophilic Graphs via Disentangled Representation Learning [PDF]

, 2022
Link prediction is an important task that has wide applications in various domains. However, the majority of existing link prediction approaches assume the given graph follows homophily assumption, and designs similarity-based heuristics or ...
Aggarwal, Charu, Wang, Suhang, Zhou, Shijie, Guo, Zhimeng, Zhang, Xiang   +4 more
core   +1 more source

Label-Wise Graph Convolutional Network for Heterophilic Graphs [PDF]

, 2023
Graph Neural Networks (GNNs) have achieved remarkable performance in modeling graphs for various applications. However, most existing GNNs assume the graphs exhibit strong homophily in node labels, i.e., nodes with similar labels are connected in the ...
Dai, Enyan, Wang, Suhang, Zhou, Shijie, Guo, Zhimeng   +3 more
core   +1 more source

Edge Directionality Improves Learning on Heterophilic Graphs [PDF]

, 2023
Graph Neural Networks (GNNs) have become the de-facto standard tool for modeling relational data. However, while many real-world graphs are directed, the majority of today's GNN models discard this information altogether by simply making the graph ...
Günnemann, Stephan, Frasca, Fabrizio, Rossi, Emanuele, Di Giovanni, Francesco, Bronstein, Michael, Charpentier, Bertrand   +5 more
core   +1 more source

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

, 2023
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, Tao, Xiaofeng, Nan, Guoshun, Xiong, Tianyu, Sun, Lijuan, Deng, Wendi, Teng, Zhiyang, Qiu, Chenyang, Wang, Di   +8 more
core  

A Network Analysis-Driven Framework for Factual Explainability of Knowledge Graphs

IEEE Access
Knowledge Graphs are widely used to represent knowledge structures in complex domains. In most real-world scenarios, these knowledge structures are dynamic.
Siraj Munir, Rauf Ahmed Shams Malick, Stefano Ferretti   +2 more
doaj   +1 more source

Single-Pass Contrastive Learning Can Work for Both Homophilic and Heterophilic Graph [PDF]

, 2023
Existing graph contrastive learning (GCL) techniques typically require two forward passes for a single instance to construct the contrastive loss, which is effective for capturing the low-frequency signals of node features.
Zhang, Jieyu, Kawaguchi, Kenji, Xiao, Xiaokui, Huang, Wei, Wang, Haonan, Zhu, Qi   +5 more
core   +1 more source

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

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   +1 more source

Modeling Higher-Order Interactions in Graphs Through Combinatorial Arc-Transitive Structure Using Graph Convolutional Network

IEEE Access
The analysis of networks, including social, citation, biological, and traffic networks, has become a critical research area, enabling deeper insights into complex systems across diverse fields.
Qingwei Wen
doaj   +1 more source

LDC-GAT: A Lyapunov-Stable Graph Attention Network with Dynamic Filtering and Constraint-Aware Optimization

Axioms
Graph attention networks are pivotal for modeling non-Euclidean data, yet they face dual challenges: training oscillations induced by projection-based high-dimensional constraints and gradient anomalies due to poor adaptation to heterophilic structure ...
Liping Chen, Hongji Zhu, Shuguang Han
doaj   +1 more source

ECHO: Encoding Communities via High-order Operators

Machine Learning with Applications
Community detection in attributed networks faces a fundamental divide: topological algorithms ignore semantic features, while Graph Neural Networks (GNNs) encounter significant computational bottlenecks.
Emilio Ferrara
doaj   +1 more source