xflow-net 0.0.4

a python library for graph flow

XFlow Homepage | Documentation | Paper Collection | Colab Notebooks Tutorials

XFlow is a library built upon Python to easily write and train method for a wide range of applications related to network flow problems. XFlow is organized task-wise, which provide datasets benchmarks, baselines and auxiliary implementation.

Installation

pip install xflow-net

Example

from xflow.dataset import cora, random, ba
from xflow.diffusion import ic, si
from xflow.seed import random, degree, eigen
from xflow.method.im import celf, sigma

# graphs to test
gs = [cora, random, ba]

# diffusion models to test
df = [ic, si]

# seed configurations to test
se = [random, degree, eigen]

# methods to test
me = [celf, sigma, imrank]

# configurations of experiments
rt = run(graph=gs, diffusion=df, seed=se, method=me, eval='im', epoch=10, output=['animation', 'csv', 'fig'])

[Result]

Create your own models

Benchmark Task

Influence Maximization

• simulation: greedy, CELF, and CELF++,
• proxy: pi, sigma, degree, and eigen-centrality
• sketch: RIS, SKIM, IMM

Blocking Maximization

• greedy
• pi
• sigma
• eigen-centrality
• degree

Source Localization

• NETSLEUTH (Legacy and Fast versions)
• Jordan Centrality
• LISN.

Experimental Configurations

• Graphs: Compatiable with graph objects/class by Networkx and Pytorch Geometric
• Diffusion Models: Support NDLib

Contact

Feel free to email us if you wish your work to be listed in this repo. If you notice anything unexpected, please open an issue and let us know. If you have any questions or are missing a specific feature, feel free to discuss them with us. We are motivated to constantly make XFlow even better.