bottleneck
how_attentive_are_gats
Our great sponsors
| bottleneck | how_attentive_are_gats | |
|---|---|---|
| 2 | 1 | |
| 90 | 275 | |
| - | 6.2% | |
| 0.0 | 0.0 | |
| about 2 years ago | about 2 years ago | |
| Python | Python | |
| MIT License | - |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
bottleneck
-
[D] Dr. Petar Veličković (Deepmind) - Categories, Graphs, Reasoning and Graph Expander Propagation
Found relevant code at https://github.com/tech-srl/bottleneck + all code implementations here
-
[N] New Transport Planning Dataset for Deep Graph Neural Networks
Code for https://arxiv.org/abs/2006.05205 found: https://github.com/tech-srl/bottleneck
how_attentive_are_gats
-
Graph Attention Networks (GAT) v2 implementation with side-by-side notes
Code for https://arxiv.org/abs/2105.14491 found: https://github.com/tech-srl/how_attentive_are_gats
What are some alternatives?
GraphMixerNetworks - Official Implementation of Graph Mixer Networks
GAT - Graph Attention Networks (https://arxiv.org/abs/1710.10903)
grand-cypher - Implementation of the Cypher language for searching NetworkX graphs
transformer-pytorch - Transformer: PyTorch Implementation of "Attention Is All You Need"
osmnx - OSMnx is a Python package to easily download, model, analyze, and visualize street networks and other geospatial features from OpenStreetMap.
pytorch-GAT - My implementation of the original GAT paper (Veličković et al.). I've additionally included the playground.py file for visualizing the Cora dataset, GAT embeddings, an attention mechanism, and entropy histograms. I've supported both Cora (transductive) and PPI (inductive) examples!
code2vec - TensorFlow code for the neural network presented in the paper: "code2vec: Learning Distributed Representations of Code"
TransportPlanningDataset - A graph based strategic transport planning dataset, aimed at creating the next generation of deep graph neural networks for transfer learning. Based on simulation results of the Four Step Model in PTV Visum.