Results 1 to 10 of about 1,367 (116)
Auto-HeG: Automated Graph Neural Network on Heterophilic Graphs
Proceedings of the ACM Web Conference 2023, 2023 Graph neural architecture search (NAS) has gained popularity in automatically designing powerful graph neural networks (GNNs) with relieving human efforts. However, existing graph NAS methods mainly work under the homophily assumption and overlook another important graph property, i.e., heterophily, which exists widely in various real-world ...
xin zheng, Miao Zhang, Chunyang Chen
exaly +3 more sources
MUSE: Multi-View Contrastive Learning for Heterophilic Graphs
Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, 2023 In recent years, self-supervised learning has emerged as a promising approach in addressing the issues of label dependency and poor generalization performance in traditional GNNs. However, existing self-supervised methods have limited effectiveness on heterophilic graphs, due to the homophily assumption that results in similar node representations for ...
Mengyi Yuan, Minjie Chen, Xiang Li
exaly +3 more sources
CAT: A causal graph attention network for trimming heterophilic graphs
Information Sciences25 pages, 18 figures, 5 ...
Silu He, Haifeng Li
exaly +3 more sources
The Heterophilic Snowflake Hypothesis: Training and Empowering GNNs for Heterophilic Graphs
Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data MiningGraph Neural Networks (GNNs) have become pivotal tools for a range of graph-based learning tasks. Notably, most current GNN architectures operate under the assumption of homophily, whether explicitly or implicitly. While this underlying assumption is frequently adopted, it is not universally applicable, which can result in potential shortcomings in ...
Kun Wang, Guibin Zhang, Xinnan Zhang
exaly +3 more sources
Label-Wise Graph Convolutional Network for Heterophilic Graphs
CoRR, 2021 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 graphs.
Enyan Dai +3 more
openaire +5 more sources
On Local Aggregation in Heterophilic Graphs
CoRR, 2021 Many recent works have studied the performance of Graph Neural Networks (GNNs) in the context of graph homophily - a label-dependent measure of connectivity. Traditional GNNs generate node embeddings by aggregating information from a node's neighbors in the graph.
Hesham Mostafa +2 more
openaire +2 more sources
HP-GMN: Graph Memory Networks for Heterophilous Graphs
2022 IEEE International Conference on Data Mining (ICDM), 2022 Graph neural networks (GNNs) have achieved great success in various graph problems. However, most GNNs are Message Passing Neural Networks (MPNNs) based on the homophily assumption, where nodes with the same label are connected in graphs. Real-world problems bring us heterophily problems, where nodes with different labels are connected in graphs. MPNNs
Junjie Xu +3 more
openaire +2 more sources
Edge Directionality Improves Learning on Heterophilic Graphs
CoRR, 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 undirected.
Emanuele Rossi +5 more
openaire +3 more sources
Junctional Adhesion Molecule-C Mediates the Recruitment of Embryonic-Endothelial Progenitor Cells to the Perivascular Niche during Tumor Angiogenesis [PDF]
, 2020 The homing of Endothelial Progenitor Cells (EPCs) to tumor angiogenic sites has been described as a multistep process, involving adhesion, migration, incorporation and sprouting, for which the underlying molecular and cellular mechanisms are yet to be ...
Bieback, Karen +6 more
core +1 more source
Binding between the neural cell adhesion molecules axonin-1 and Nr- CAM/Bravo is involved in neuron-glia interaction [PDF]
, 1995 Neural cell adhesion molecules of the immunoglobulin superfamily mediate cellular interactions via homophilic binding to identical molecules and heterophilic binding to other family members or structurally unrelated cell-surface glycoproteins.
Buchstaller, Andrea +5 more
core +4 more sources