Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patterns

Benchmark Model Rank Results
node-classification-on-cora-48-32-20-fixed-splitsWRGAT#61:1 Accuracy: 88.20 ± 2.26
node-classification-on-non-homophilic-heterophilic-graphs-on-film-48-32-20-fixed-splitsWRGAT#131:1 Accuracy: 36.53 ± 0.77
node-classification-on-non-homophilic-heterophilic-graphs-on-wisconsin-48-32-20-fixed-splitsWRGAT#141:1 Accuracy: 86.98 ± 3.78
node-classification-on-citeseer-48-32-20-fixed-splitsWRGAT#151:1 Accuracy: 76.81 ± 1.89
node-classification-on-non-homophilic-heterophilic-graphs-on-texas-48-32-20-fixed-splitsWRGAT#161:1 Accuracy: 83.62 ± 5.50
node-classification-on-non-homophilic-heterophilic-graphs-on-cornell-48-32-20-fixed-splitsWRGAT#191:1 Accuracy: 81.62 ±3.90
node-classification-on-pubmed-48-32-20-fixed-splitsWRGAT#191:1 Accuracy: 88.52 ± 0.92
node-classification-on-non-homophilic-heterophilic-graphs-on-squirrel-48-32-20-fixed-splitsWRGAT#201:1 Accuracy: 48.85 ± 0.78
node-classification-on-non-homophilic-heterophilic-graphs-on-chameleon-48-32-20-fixed-splitsWRGAT#211:1 Accuracy: 65.24 ± 0.87
node-classification-on-actorWRGAT#26Accuracy: 36.53 ± 0.77
node-classification-on-cornellWRGAT#28Accuracy: 81.62 ± 3.90
node-classification-on-non-homophilic-heterophilic-graphs-on-penn94WRGAT#281:1 Accuracy: 74.32 ± 0.53
node-classification-on-texasWRGAT#28Accuracy: 83.62 ± 5.50
node-classification-on-squirrelWRGAT#30Accuracy: 48.85 ± 0.78
node-classification-on-chameleonWRGAT#32Accuracy: 65.24 ± 0.87
node-classification-on-penn94WRGAT#32Accuracy: 74.32 ± 0.53