Graph Embeddings
Laplacian Positional Encodings
Introduced by Dwivedi et al. in Benchmarking Graph Neural NetworksLaplacian eigenvectors represent a natural generalization of the Transformer positional encodings (PE) for graphs as the eigenvectors of a discrete line (NLP graph) are the cosine and sinusoidal functions. They help encode distance-aware information (i.e., nearby nodes have similar positional features and farther nodes have dissimilar positional features).
Hence, Laplacian Positional Encoding (PE) is a general method to encode node positions in a graph. For each node, its Laplacian PE is the k smallest non-trivial eigenvectors.
Source: Benchmarking Graph Neural Networks
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Node Classification | 34 | 5.71% |
| Graph Learning | 34 | 5.71% |
| Graph Representation Learning | 24 | 4.03% |
| Graph Neural Network | 22 | 3.70% |
| Prediction | 18 | 3.03% |
| Link Prediction | 17 | 2.86% |
| Graph Regression | 17 | 2.86% |
| Graph Classification | 17 | 2.86% |
| Graph Generation | 12 | 2.02% |
