Graph Property Prediction
35 papers with code • 4 benchmarks • 2 datasets
Benchmarks
These leaderboards are used to track progress in Graph Property Prediction
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
OGB
PCQM4Mv2-LSC
Subtasks
Most implemented papers
How Attentive are Graph Attention Networks?
tech-srl/how_attentive_are_gats
•
•
ICLR 2022
Because GATs use a static attention mechanism, there are simple graph problems that GAT cannot express: in a controlled problem, we show that static attention hinders GAT from even fitting the training data.
Large-scale Robust Deep AUC Maximization: A New Surrogate Loss and Empirical Studies on Medical Image Classification
Optimization-AI/LibAUC
•
•
ICCV 2021
Our studies demonstrate that the proposed DAM method improves the performance of optimizing cross-entropy loss by a large margin, and also achieves better performance than optimizing the existing AUC square loss on these medical image classification tasks.
Do Transformers Really Perform Bad for Graph Representation?
Our key insight to utilizing Transformer in the graph is the necessity of effectively encoding the structural information of a graph into the model.
DeeperGCN: All You Need to Train Deeper GCNs
dmlc/dgl
•
•
Graph Convolutional Networks (GCNs) have been drawing significant attention with the power of representation learning on graphs.
Global Self-Attention as a Replacement for Graph Convolution
shamim-hussain/egt_pytorch
•
•
The resultant framework - which we call Edge-augmented Graph Transformer (EGT) - can directly accept, process and output structural information of arbitrary form, which is important for effective learning on graph-structured data.
Recipe for a General, Powerful, Scalable Graph Transformer
We propose a recipe on how to build a general, powerful, scalable (GPS) graph Transformer with linear complexity and state-of-the-art results on a diverse set of benchmarks.
Triplet Interaction Improves Graph Transformers: Accurate Molecular Graph Learning with Triplet Graph Transformers
We also obtain SOTA results on QM9, MOLPCBA, and LIT-PCBA molecular property prediction benchmarks via transfer learning.
Weisfeiler and Lehman Go Cellular: CW Networks
twitter-research/cwn
•
•
NeurIPS 2021
Nevertheless, these models can be severely constrained by the rigid combinatorial structure of Simplicial Complexes (SCs).
Nested Graph Neural Networks
muhanzhang/nestedgnn
•
•
NeurIPS 2021
The key is to make each node representation encode a subgraph around it more than a subtree.
Global Concept Explanations for Graphs by Contrastive Learning
aimat-lab/megan_global_explanations
•
•
Overall, our results show promising capability to extract the underlying structure-property relationships for complex graph property prediction tasks.
