Node Classification On Citeseer

Metriken

Accuracy

Validation

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Modellname	Accuracy	Validation	Paper Title	Repository
MTGAE	71.80%	YES	Multi-Task Graph Autoencoders
PPNP	75.83%	YES	Predict then Propagate: Graph Neural Networks meet Personalized PageRank
GOCN	71.8%	-	Robust Graph Data Learning via Latent Graph Convolutional Representation	-
SNoRe	66.6	-	SNoRe: Scalable Unsupervised Learning of Symbolic Node Representations	-
SplineCNN	79.20%	-	SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels
Graph-MLP + SWA	77.99 ± 1.57%	-	The Split Matters: Flat Minima Methods for Improving the Performance of GNNs
ACMII-Snowball-3	81.56 ± 1.15	-	Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?	-
LDS-GNN	75.0	-	Learning Discrete Structures for Graph Neural Networks
alpha-LoNGAE	71.60%	-	Learning to Make Predictions on Graphs with Autoencoders
GResNet(GCN)	72.7%	-	GResNet: Graph Residual Network for Reviving Deep GNNs from Suspended Animation
APPNP	70.0 ± 1.4	-	Fast Graph Representation Learning with PyTorch Geometric
ACM-Snowball-2	81.58 ± 1.23	-	Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?	-
PairE	75.53	-	Graph Representation Learning Beyond Node and Homophily
PathNet	-	-	Beyond Homophily: Structure-aware Path Aggregation Graph Neural Network
GResNet(GAT)	73.5%	-	GResNet: Graph Residual Network for Reviving Deep GNNs from Suspended Animation
CGT	76.59±0.98	-	Mitigating Degree Biases in Message Passing Mechanism by Utilizing Community Structures
Graphite	71.0 ± 0.07	-	Graphite: Iterative Generative Modeling of Graphs
SF-GCN	73.4%	-	Structure fusion based on graph convolutional networks for semi-supervised classification	-
hpGAT	73.0%	-	hpGAT: High-order Proximity Informed Graph Attention Network	-
AdaGCN	76.22 ± 0.20	-	AdaGCN: Adaboosting Graph Convolutional Networks into Deep Models

0 of 70 row(s) selected.