A collection of important graph embedding, classification and representation learning papers with implementations.

A parallel implementation of "graph2vec: Learning Distributed Representations of Graphs" (MLGWorkshop 2017).

Source code for our AAAI paper "Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks".

A scalable Gensim implementation of "Learning Role-based Graph Embeddings" (IJCAI 2018).

A Persistent Weisfeiler–Lehman Procedure for Graph Classification

Code and dataset to test empirically the expressive power of graph pooling operators presented as presented at NeurIPS 2023

DEMO-Net: Degree-specific Graph Neural Networks for Node and Graph Classification

Python code for "M. Zhang, Y. Chen, Weisfeiler-Lehman Neural Machine for Link Prediction, KDD 2017"

Library for the analysis of time-evolving graphs

Test graph isomorphism with 1-WL for different graph classes and labelings

Learning to Aggregate on Structured Data

DRESS: A Continuous Framework for Structural Graph Refinement

Implementation of the algorithm described in the paper "On the Power of Color Refinement".

Official repository for "Improving Subgraph-GNNs via Edge-Level Ego-Network Encodings" based on the official GNN-As-Kernel repository.

Project 1 - unifesp master's degree course

Ausarbeitung für das Seminar Algorithm Engineering an der TU Dortmund zum Paper "On the Power of Color Refinement" von Arvind et al.

This project implements a Machine Learning pipeline for chemical reaction classification using Support Vector Machines (SVM) and Weisfeiler-Leman (WL) Graph Kernels.

1-WL Graph Isomorphism Test

The goal here is to use a graph kernel and a manifold learning technique in conjunction with Support Vector Machines to enhance the SVM classification.

A short review on Graph Neural Networks done during the Master's degree Mathematics, Vision, Learning (MVA) from ENS Paris-Saclay.