GitHub - lithafnium/Network-Compression

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 47 Commits
CLIP_experiments		CLIP_experiments
__pycache__		__pycache__
accuracy		accuracy
coin		coin
data		data
gan		gan
plots		plots
.gitignore		.gitignore
README.txt		README.txt
build_graph.py		build_graph.py
cs222.yml		cs222.yml
graph.txt		graph.txt
graph_model.py		graph_model.py
loss_sizes.json		loss_sizes.json
main.py		main.py
model.json.gzip		model.json.gzip
model.pt		model.pt
model.py		model.py
mytestfile.hdf5		mytestfile.hdf5
out.txt		out.txt
plot_predictions.py		plot_predictions.py
run.sh		run.sh
size_estimator.py		size_estimator.py
train.py		train.py
util.py		util.py
utils.py		utils.py
xgboost_classifier.py		xgboost_classifier.py

Repository files navigation

Facebook Large Page-Page Network

Description

This webgraph is a page-page graph of verified Facebook sites. Nodes represent official Facebook pages while the links are mutual likes between sites. Node features are extracted from the site descriptions that the page owners created to summarize the purpose of the site. This graph was collected through the Facebook Graph API in November 2017 and restricted to pages from 4 categories which are defined by Facebook. These categories are: politicians, governmental organizations, television shows and companies. The task related to this dataset is multi-class node classification for the 4 site categories.

- Directed: No.
- Node features: Yes.
- Edge features: No.
- Node labels: Yes. Binary-labeled.
- Temporal: No.

|   | Facebook  |
|---|---|
| Nodes |22,470   | 
| Edges | 171,002  |
| Density |  0.001 | 
| Transitvity | 0.232| 

Possible tasks

- Multi-class node classification
- Link prediction
- Community detection
- Network visualization