Node Classification On Non Homophilic 2

Metriken

1:1 Accuracy

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Modellname	1:1 Accuracy	Paper Title
ACM-SGC-1	93.61 ± 1.55	Revisiting Heterophily For Graph Neural Networks
MixHop	76.39 ± 7.66	MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing
GraphSAGE	79.03 ± 1.20	Inductive Representation Learning on Large Graphs
ACM-GCNII	92.46 ± 1.97	Revisiting Heterophily For Graph Neural Networks
Snowball-3	83.11 ± 3.2	Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks
SGC-2	81.31 ± 3.3	Simplifying Graph Convolutional Networks
FAGCN	88.85 ± 4.39	Beyond Low-frequency Information in Graph Convolutional Networks
Geom-GCN*	67.57	Geom-GCN: Geometric Graph Convolutional Networks
ACM-GCN++	96.56 ± 2	Revisiting Heterophily For Graph Neural Networks
ACMII-GCN+	95.41 ± 2.82	Revisiting Heterophily For Graph Neural Networks
ACMII-GCN++	94.75 ± 2.91	Revisiting Heterophily For Graph Neural Networks
ACMII-Snowball-3	94.75 ± 3.09	Revisiting Heterophily For Graph Neural Networks
ACMII-Snowball-2	95.25 ± 1.55	Revisiting Heterophily For Graph Neural Networks
ACM-GCN+	94.92 ± 2.79	Revisiting Heterophily For Graph Neural Networks
SGC-1	83.28 ± 5.43	Simplifying Graph Convolutional Networks
H2GCN	85.90 ± 3.53	Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs
GCNII*	88.52 ± 3.02	Simple and Deep Graph Convolutional Networks
GCNII	82.46 ± 4.58	Simple and Deep Graph Convolutional Networks
APPNP	91.18 ± 0.70	Predict then Propagate: Graph Neural Networks meet Personalized PageRank
GCN+JK	80.66 ± 1.91	Revisiting Heterophily For Graph Neural Networks

0 of 32 row(s) selected.