OpenCodePapers

node-classification-on-penn94

Node Classification
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeAccuracyModelNameReleaseDate
Feature Selection: Key to Enhance Node Classification with Graph Neural Networks✓ Link86.09±0.56Dual-Net GNN2023-01-25
Revisiting Heterophily For Graph Neural Networks✓ Link86.08 ± 0.43ACM-GCN++2022-10-14
Revisiting Heterophily For Graph Neural Networks✓ Link85.95 ± 0.26ACMII-GCN++2022-10-14
Finding Global Homophily in Graph Neural Networks When Meeting Heterophily✓ Link85.74±0.42GloGNN++2022-05-15
Finding Global Homophily in Graph Neural Networks When Meeting Heterophily✓ Link85.57 ± 0.35GloGNN2022-05-15
Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification✓ Link85.11±0.39GNNMoE(GCN-like P)2024-12-11
Revisiting Heterophily For Graph Neural Networks✓ Link85.05 ± 0.19ACM-GCN+2022-10-14
Revisiting Heterophily For Graph Neural Networks✓ Link84.95 ± 0.43ACMII-GCN+2022-10-14
Diffusion-Jump GNNs: Homophiliation via Learnable Metric Filters✓ Link84.84±0.34DJ-GNN2023-06-29
Clarify Confused Nodes via Separated Learning✓ Link84.74 ± 0.28NCGCN2023-06-04
Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods✓ Link84.71 ± 0.52LINKX2021-10-27
Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification✓ Link84.05±0.37GNNMoE(SAGE-like P)2024-12-11
MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing✓ Link83.47 ± 0.71MixHop2019-04-30
Simple and Deep Graph Convolutional Networks✓ Link82.92 ± 0.59GCNII2020-07-04
Semi-Supervised Classification with Graph Convolutional Networks✓ Link82.47 ± 0.27GCN2016-09-09
Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification✓ Link81.98±0.47GNNMoE(GAT-like P)2024-12-11
Clarify Confused Nodes via Separated Learning✓ Link81.77 ± 0.71NCSAGE2023-06-04
New Benchmarks for Learning on Non-Homophilous Graphs✓ Link81.63 ± 0.54GCNJK2021-04-03
Graph Attention Networks✓ Link81.53 ± 0.55GAT2017-10-30
Adaptive Universal Generalized PageRank Graph Neural Network✓ Link81.38 ± 0.16GPRGCN2020-06-14
Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs✓ Link81.31 ± 0.60H2GCN2020-06-20
New Benchmarks for Learning on Non-Homophilous Graphs✓ Link80.79 ± 0.49LINK 2021-04-03
New Benchmarks for Learning on Non-Homophilous Graphs✓ Link80.69 ± 0.36GATJK2021-04-03
Combining Label Propagation and Simple Models Out-performs Graph Neural Networks✓ Link78.40 ± 3.12C&S 2-hop2020-10-27
Simplifying Graph Convolutional Networks✓ Link76.09 ± 0.45SGC 2-hop2019-02-19
Predict then Propagate: Graph Neural Networks meet Personalized PageRank✓ Link74.33 ± 0.38APPNP2018-10-14
Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patterns✓ Link74.32 ± 0.53WRGAT2021-06-11
Combining Label Propagation and Simple Models Out-performs Graph Neural Networks✓ Link74.28 ± 1.19C&S 1-hop 2020-10-27
New Benchmarks for Learning on Non-Homophilous Graphs✓ Link74.13 ± 0.46L Prop 2-hop2021-04-03
New Benchmarks for Learning on Non-Homophilous Graphs✓ Link73.61 ± 0.40MLP2021-04-03
Simplifying Graph Convolutional Networks✓ Link66.79 ± 0.27SGC 1-hop2019-02-19
New Benchmarks for Learning on Non-Homophilous Graphs✓ Link63.21 ± 0.39L Prop 1-hop2021-04-03
Check out how to contribute new results.