VERtex Similarity Embeddings (VERSE) is a simple, versatile, and memory-efficient method that derives graph embeddings explicitly calibrated to preserve the distributions of a selected vertex-to-vertex similarity measure. VERSE learns such embeddings by training a single-layer neural network.
Source: Tsitsulin et al.
Image source: Tsitsulin et al.
Source: VERSE: Versatile Graph Embeddings from Similarity MeasuresPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Link Prediction | 4 | 6.56% |
Anatomy | 3 | 4.92% |
Translation | 3 | 4.92% |
Computed Tomography (CT) | 3 | 4.92% |
Node Classification | 3 | 4.92% |
Benchmarking | 2 | 3.28% |
Retrieval | 2 | 3.28% |
Sentence | 2 | 3.28% |
Decoder | 2 | 3.28% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |