2022
DOI: 10.48550/arxiv.2205.07308
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Finding Global Homophily in Graph Neural Networks When Meeting Heterophily

Abstract: We investigate graph neural networks on graphs with heterophily. Some existing methods amplify a node's neighborhood with multi-hop neighbors to include more nodes with homophily. However, it is a significant challenge to set personalized neighborhood sizes for different nodes. Further, for other homophilous nodes excluded in the neighborhood, they are ignored for information aggregation. To address these problems, we propose two models GloGNN and GloGNN++, which generate a node's embedding by aggregating info… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
6
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
4
1
1

Relationship

1
5

Authors

Journals

citations
Cited by 6 publications
(6 citation statements)
references
References 26 publications
0
6
0
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%
“…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%
“…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%
“…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%