Link Property Prediction On Ogbl Citation2
Metrics
Ext. data
Number of params
Test MRR
Validation MRR
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Ext. data | Number of params | Test MRR | Validation MRR |
|---|---|---|---|---|
| can-gnns-learn-link-heuristics-a-concise | No | 372674 | 0.8891 ± 0.0005 | 0.8892 ± 0.0005 |
| open-graph-benchmark-datasets-for-machine | No | 281113505 | 0.5186 ± 0.0443 | 0.5181 ± 0.0436 |
| Model 3 | No | 0 | 0.5147 ± 0.0000 | 0.5119 ± 0.0000 |
| graphgpt-graph-learning-with-generative-pre | No | 46784128 | 0.9055 ± 0.0016 | 0.9042 ± 0.0014 |
| inductive-representation-learning-on-large | No | 460289 | 0.8044 ± 0.0010 | 0.8054 ± 0.0009 |
| inductive-representation-learning-on-large | No | 460289 | 0.8260 ± 0.0036 | 0.8263 ± 0.0033 |
| adaptive-graph-diffusion-networks-with-hop | No | 306716 | 0.8549 ± 0.0029 | 0.8556 ± 0.0033 |
| network-in-graph-neural-network | No | 1134402 | 0.8891 ± 0.0022 | 0.8879 ± 0.0022 |
| node2vec-scalable-feature-learning-for | No | 374911105 | 0.6141 ± 0.0011 | 0.6124 ± 0.0011 |
| circle-feature-graphormer-can-circle-features | No | 686253 | 0.8997 ± 0.0015 | 0.8987 ± 0.0011 |
| algorithm-and-system-co-design-for-efficient | No | 79617 | 0.8883 ± 0.0018 | 0.8891 ± 0.0021 |
| pure-message-passing-can-estimate-common | No | 749757283 | 0.9072 ± 0.0012 | 0.9074 ± 0.0011 |
| simplifying-subgraph-representation-learning | No | 142275001 | 0.8814 ± 0.0008 | 0.8809 ± 0.0074 |
| graphgpt-graph-learning-with-generative-pre | No | 133096832 | 0.9305 ± 0.0020 | 0.9295 ± 0.0022 |
| graphsaint-graph-sampling-based-inductive | No | 296449 | 0.7985 ± 0.0040 | 0.7975 ± 0.0039 |
| Model 16 | No | 749558528 | 0.8432 ± 0.0003 | 0.8422 ± 0.0002 |
| semi-supervised-classification-with-graph | No | 296449 | 0.8474 ± 0.0021 | 0.8479 ± 0.0023 |
| cluster-gcn-an-efficient-algorithm-for | No | 296449 | 0.8004 ± 0.0025 | 0.7994 ± 0.0025 |
| Model 19 | No | 256802 | 0.8957 ± 0.0010 | 0.8948 ± 0.0008 |
| Model 20 | No | 0 | 0.5189 ± 0.0000 | 0.5167 ± 0.0000 |
| pairwise-learning-for-neural-link-prediction | No | 146514551 | 0.8492 ± 0.0029 | 0.8490 ± 0.0031 |
| Model 22 | No | 166531 | 0.8796 ± 0.0008 | 0.8793 ± 0.0008 |
| revisiting-graph-neural-networks-for-link-1 | No | 260802 | 0.8767 ± 0.0032 | 0.8757 ± 0.0031 |