OpenCodePapers

node-classification-on-cornell-60-20-20

Node Classification
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCode1:1 AccuracyModelNameReleaseDate
Revisiting Heterophily For Graph Neural Networks✓ Link95.9 ± 1.83ACMII-GCN2022-10-14
Revisiting Heterophily For Graph Neural Networks✓ Link95.25 ± 1.55ACMII-Snowball-22022-10-14
Revisiting Heterophily For Graph Neural Networks✓ Link95.08 ± 3.11ACM-Snowball-22022-10-14
Revisiting Heterophily For Graph Neural Networks✓ Link94.92 ± 2.79ACM-GCN+2022-10-14
Revisiting Heterophily For Graph Neural Networks✓ Link94.75 ± 3.8ACM-GCN2022-10-14
Revisiting Heterophily For Graph Neural Networks✓ Link94.26 ± 2.57ACM-Snowball-32022-10-14
Revisiting Heterophily For Graph Neural Networks✓ Link93.93 ± 1.05ACM-GCN++2022-10-14
Revisiting Heterophily For Graph Neural Networks✓ Link93.93 ± 3.03ACMII-GCN+2022-10-14
Revisiting Heterophily For Graph Neural Networks✓ Link93.77 ± 1.91ACM-SGC-12022-10-14
Revisiting Heterophily For Graph Neural Networks✓ Link93.77 ± 2.17ACM-SGC-22022-10-14
Revisiting Heterophily For Graph Neural Networks✓ Link93.61 ± 2.79ACMII-Snowball-32022-10-14
Revisiting Heterophily For Graph Neural Networks✓ Link93.44 ± 2.74ACM-GCNII*2022-10-14
Revisiting Heterophily For Graph Neural Networks✓ Link92.62 ± 3.13ACM-GCNII2022-10-14
Revisiting Heterophily For Graph Neural Networks✓ Link92.62 ± 2.57ACMII-GCN++2022-10-14
BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation✓ Link92.13 ± 1.64BernNet2021-06-21
Predict then Propagate: Graph Neural Networks meet Personalized PageRank✓ Link91.80 ± 0.63APPNP2018-10-14
Adaptive Universal Generalized PageRank Graph Neural Network✓ Link91.36 ± 0.70GPRGNN2020-06-14
Revisiting Heterophily For Graph Neural Networks✓ Link91.30 ± 0.70MLP-22022-10-14
Simple and Deep Graph Convolutional Networks✓ Link90.49 ± 4.45GCNII*2020-07-04
Simple and Deep Graph Convolutional Networks✓ Link89.18 ± 3.96GCNII2020-07-04
Beyond Low-frequency Information in Graph Convolutional Networks✓ Link88.03 ± 5.6FAGCN2021-01-04
Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs✓ Link86.23 ± 4.71H2GCN2020-06-20
Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks✓ Link82.95 ± 2.1Snowball-32019-06-05
Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks✓ Link82.62 ± 2.34Snowball-22019-06-05
Semi-Supervised Classification with Graph Convolutional Networks✓ Link82.46 ± 3.11GCN2016-09-09
Graph Attention Networks✓ Link76.00 ± 1.01GAT2017-10-30
Half-Hop: A graph upsampling approach for slowing down message passing✓ Link74.6 ± 6.06HH-GraphSAGE2023-08-17
Revisiting Heterophily For Graph Neural Networks✓ Link74.43 ± 10.24 GAT+JK2022-10-14
Half-Hop: A graph upsampling approach for slowing down message passing✓ Link72.7 ± 4.26HH-GAT2023-08-17
Simplifying Graph Convolutional Networks✓ Link72.62 ± 9.92SGC-22019-02-19
Inductive Representation Learning on Large Graphs✓ Link71.41 ± 1.24GraphSAGE2017-06-07
Simplifying Graph Convolutional Networks✓ Link70.98 ± 8.39SGC-12019-02-19
Revisiting Heterophily For Graph Neural Networks✓ Link66.56 ± 13.82GCN+JK2022-10-14
Half-Hop: A graph upsampling approach for slowing down message passing✓ Link63.24 ± 5.43HH-GCN2023-08-17
Geom-GCN: Geometric Graph Convolutional Networks✓ Link60.81Geom-GCN*2020-02-13
MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing✓ Link60.33 ± 28.53MixHop2019-04-30
Check out how to contribute new results.