Network Analysis in Python

A library for graph deep learning research

🗡 A tool to visualize Dagger 2 dependency graphs

NetworKit is a growing open-source toolkit for large-scale network analysis.

An optimized graphs package for the Julia programming language

Efficient Graph Generation with Graph Recurrent Attention Networks, Deep Generative Model of Graphs, Graph Neural Networks, NeurIPS 2019

[EMNLP'2024] "OpenGraph: Towards Open Graph Foundation Models"

🔧 Python Random Graph Generator

Official Code Repository for the paper "Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations" (ICML 2022)

Exports task execution graph as .dot file

Awesome Graph Diffusion Models is a collection of graph generation works, including papers, codes and datasets.

Generate graphs with gnuplot or matplotlib (Python) from sar data

[TMLR] GraphMaker: Can Diffusion Models Generate Large Attributed Graphs?

Official repository for "Categorical Normalizing Flows via Continuous Transformations"

[ICLR 2024] "Latent 3D Graph Diffusion" by Yuning You, Ruida Zhou, Jiwoong Park, Haotian Xu, Chao Tian, Zhangyang Wang, Yang Shen

A library for graph analysis written Julia.

DPPIN: A Biological Repository of Dynamic Protein-Protein Interaction Network Data, IEEE BigData 2022

Implementation for the paper: GraphGDP: Generative Diffusion Processes for Permutation Invariant Graph Generation

Graphica is an open-source graph crate for Rust that allows for the generation, manipulation and canonization of multi-edge graphs with mixed directed and undirected edges and arbitrary node and edge data.

This repository contains PyTorch implementation of the following paper: "Order Matters: Probabilistic Modeling of Node Sequence for Graph Generation"

[ICLR 2025 Spotlight] LayerDAG: A Layerwise Autoregressive Diffusion Model of Directed Acyclic Graphs

MultiGraphGAN for predicting multiple target graphs from a source graph using geometric deep learning.

Hypothesis strategy to generate NetworkX graphs.

The differential drive has an ESP32 board for wireless connectivity a Client-Server network is established between the server laptop and client ESP to transmit the coordinates to the robot. An overhead camera is used to visually survey the obstacle course and image processing is used to segment the obstacles and the robot from the captured images. Further, the obstacle course is used to make a "visibility graph" and finally "Dijkstra's shortest path algorithm" is used to search the shortest pah from the robot position to the goal position. Kinematic Equations of the differential drive are used to drive the robot on the path obtained. Finally, a pygame simulation of the robot movement is made to predict the behavior of the robot in real world and the robot is driven using this simulation.

Pre-trained models for our work on Temporal Graph Generation

A Temporal Networks Library written in Python

Implementation of "Learning Deep Generative Models"

An aggregation of algorithms, data structures and supporting crates

Analyzing Complex Networks with Python

Python tool for generating undirected weighted graphs representing road networks.