graph-mining

A pytorch adversarial library for attack and defense methods on images and graphs

Papers about pretraining and self-supervised learning on Graph Neural Networks (GNN).

A scikit-learn compatible library for graph kernels

Distributed Graph Analytics with Apache Flink

Implementation of the paper "Adversarial Attacks on Neural Networks for Graph Data".

Implementation of the paper "NetGAN: Generating Graphs via Random Walks".

Implementation of the KDD 2020 paper "Graph Structure Learning for Robust Graph Neural Networks"

Python implementation of frequent subgraph mining algorithm gSpan. Directed graphs are supported.

Implementation of the paper "Adversarial Attacks on Graph Neural Networks via Meta Learning".

A lightweight implementation of Walklets from "Don't Walk Skip! Online Learning of Multi-scale Network Embeddings" (ASONAM 2017).

Python toolbox to evaluate graph vulnerability and robustness (CIKM 2021)

GraMi is a novel framework for frequent subgraph mining in a single large graph, GraMi outperforms existing techniques by 2 orders of magnitudes. GraMi supports finding frequent subgraphs as well as frequent patterns, Compared to subgraphs, patterns offer a more powerful version of matching that captures transitive interactions between graph nodes (like friend of a friend) which are very common in modern applications. Also, GraMi supports user-defined structural and semantic constraints over the results, as well as approximate results. For more details, check our paper: Mohammed Elseidy, Ehab Abdelhamid, Spiros Skiadopoulos, and Panos Kalnis. GRAMI: Frequent Subgraph and Pattern Mining in a Single Large Graph. PVLDB, 7(7):517-528, 2014.

Implementation of paper "Self-supervised Learning on Graphs:Deep Insights and New Directions"

Python Implementation for Random Walk with Restart (RWR)

A curated list of awesome graph representation learning.

My ML related stuff including notebooks, codes and a curated list of various useful resources such as books and softwares. Almost everything mentioned here is free(as speech not free food) or open-source.

An alternative implementation of Recursive Feature and Role Extraction (KDD11 & KDD12)

Companion repository for the KDD'18 hands-on tutorial on Higher-Order Data Analytics for Temporal Network Data

gBolt--very fast implementation for gSpan algorithm in data mining

Overlapping community detection in Large-Scale Networks using BigCLAM model build on Apache Spark

👪 Social Network Analysis Papers

Core streaming heterogeneous graph clustering and anomaly detection code (KDD 2016)

Implementation of the WSDM 2021 paper "Node Similarity Preserving Graph Convolutional Networks"

Implementation of paper "Transferring Robustness for Graph Neural Network Against Poisoning Attacks".

"Explainable classification of brain networks via contrast subgraphs" - T. Lanciano, F. Bonchi, A. Gionis

Functions for creating and analyzing word co-occurrence networks in Python and R

Graph database developed on Go

Mining graph streams using dictionary-based compression

Code for "Hierarchical Propagation Networks for Fake News Detection: Investigation and Exploitation"

Pytorch implementation of gnn meta attack (mettack). Paper title: Adversarial Attacks on Graph Neural Networks via Meta Learning.