Finding Global Homophily in Graph Neural Networks When Meeting Heterophily

Li, Xiang; Renyu, Zhu,; Yang, Cheng; Shan, Caihua; Luo, Siqiang; Li, Dongsheng; Qian, Weining

doi:10.48550/arxiv.2205.07308

Cited by 6 publications

(6 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…52 GloGNN and GloGNN++ aggregates representations from global nodes to the center node. 53 Illustrated in Table 3, GD receives the accuracy of 87.26%, 72.47%, and 86.73% on Cornell, Chameleon, and Texas data set, respectively. It achieves the SOTA performance in two out of three data sets under the node classification task.…”

Section: Comparison With Sota Approaches On More Data Setsmentioning

confidence: 99%

Graph Decipher: A transparent dual‐attention graph neural network to understand the message‐passing mechanism for the node classification

Pang¹,

Liu²

2022

Int J of Intelligent Sys

View full text Add to dashboard Cite

Graph neural networks (GNNs) can be effectively applied to solve many real-world problems across widely diverse fields. Their success is inseparable from the message-passing mechanisms evolving over the years. However, current mechanisms treat all node features equally at the macro-level (node-level), and the optimal aggregation method has not yet been explored. In this paper, we propose a new GNN called Graph Decipher (GD), which transparentizes the message flows of node features from micro-level (feature-level) to global-level and boosts the performance on node classification tasks.Besides, to reduce the computational burden caused by investigating message-passing, only the relevant representative node attributes are extracted by graph feature filters, allowing calculations to be performed in a category-oriented manner. Experiments on 10 node classification data sets show that GD achieves state-ofthe-art performance while imposing a substantially lower computational cost. Additionally, since GD has the ability to explore the representative node attributes

show abstract

Section: Comparison With Sota Approaches On More Data Setsmentioning

confidence: 99%

Graph Decipher: A transparent dual‐attention graph neural network to understand the message‐passing mechanism for the node classification

Pang¹,

Liu²

2022

Int J of Intelligent Sys

View full text Add to dashboard Cite

show abstract

“…ACM-GCN [14], GeomGCN [10], H 2 GCN [28], HOC-GCN [29], BM-GCN [11], GloGNN++ [30], Auto-HeG [31], which are designed with the heterophily assumption.…”

Section: Baselinesmentioning

confidence: 99%

“…Mixing high-order neighbors expects to aggregate more homophilic nodes and remove heterophilic nodes. Specific introduction is as follows: Geom-GCN [10] proposes a novel geometric aggregation scheme to acquire more homophilic neighbors; BM-GCN [11] explores block-guided neighbors and conducts classified aggregation for both homophilic and heterophilic nodes; GloGNN [30] learns a coefficient matrix from graph and utilizes it to aggregate nodes with global homophily. HOC-GCN [29] incorporate a learnable homophily degree matrix into graph convolution framework for modeling the homophily and heterophily of networks.…”

Section: Heterophily-based Gnnsmentioning

confidence: 99%

VR-GNN: variational relation vector graph neural network for modeling homophily and heterophily

Shi,

Cao,

et al. 2024

World Wide Web

View full text Add to dashboard Cite

Graph Neural Networks (GNNs) have achieved remarkable success in diverse realworld applications. Traditional GNNs are designed based on homophily, which leads to poor performance under heterophily scenarios. Most current solutions deal with heterophily mainly by modeling the heterophily edges as data noises or high-frequency signals, treating all heterophilic edges as being of the same semantic. Consequently, they ignore the rich semantic information of these edges in heterophily graphs. To overcome this critic problem, we propose a novel GNN model based on relation vector translation named as Variational Relation Vector Graph Neural Network (VR-GNN). VR-GNN models relation generation and graph aggregation into an end-to-end model based on a variational inference framework. To be specific, the encoder utilizes the structure, feature and label to generate a fine-grained relation vector for each edge, which aims to infer its implicit semantic information. The decoder incorporates the generated relation vectors into the message-passing framework for deriving better node representations. We conduct extensive experiments on eight real-world datasets with different homophily-heterophily properties to verify model effectiveness. Extensive experimental results show that VR-GNN gains consistent and significant improvements against existing strong GNN methods under heterophily and competitive performance under homophily.

show abstract

“…FDGATII [61] adopts dynamic attention to preserve key feature information in the graph. GloGNN [62] achieves group-wise optimization by gathering information from all nodes present in the graph.…”

Section: Comparison On Heterophily Graph Datasetsmentioning

confidence: 99%

DAG: Dual Attention Graph Representation Learning for Node Classification

Lin,

Hong,

Lang

et al. 2023

Mathematics

View full text Add to dashboard Cite

Transformer-based graph neural networks have accomplished notable achievements by utilizing the self-attention mechanism for message passing in various domains. However, traditional methods overlook the diverse significance of intra-node representations, focusing solely on internode interactions. To overcome this limitation, we propose a DAG (Dual Attention Graph), a novel approach that integrates both intra-node and internode dynamics for node classification tasks. By considering the information exchange process between nodes from dual branches, DAG provides a holistic understanding of information propagation within graphs, enhancing the interpretability of graph-based machine learning applications. The experimental evaluations demonstrate that DAG excels in node classification tasks, outperforming current benchmark models across ten datasets.

show abstract

Finding Global Homophily in Graph Neural Networks When Meeting Heterophily

Cited by 6 publications

References 26 publications

Graph Decipher: A transparent dual‐attention graph neural network to understand the message‐passing mechanism for the node classification

Graph Decipher: A transparent dual‐attention graph neural network to understand the message‐passing mechanism for the node classification

VR-GNN: variational relation vector graph neural network for modeling homophily and heterophily

DAG: Dual Attention Graph Representation Learning for Node Classification

Contact Info

Product

Resources

About