The fastest Python implementation of the ForceAtlas2 graph layout algorithm, with Cython optimization for 10-100x speedup. Supports NetworkX, igraph, and raw adjacency matrices. ForceAtlas2 is a force ...

We present systematic computational analyses to investigate the influence of Matthew’s effect (i.e., “rich gets richer”) in the development, testing, and application of machine learning algorithms for ...

Quantum hardware is prone to errors and quantum error correction is a fundamental technique in quantum computing. We present an automated method to synthesize ...

As a teenager in the Czech Republic, Lenka Zdeborová glimpsed her future in an Isaac Asimov novel. A character in Asimov’s “Foundation” series invents a mathematical method for predicting the path of ...

Abstract: Many modern applications are modeled using graphs of some kind. Given a graph, assigning labels (usually called colors) to vertices is called graph coloring. Colors must be assigned so that ...

This repository contains code for our SPAA paper "Theoretically Efficient Parallel Graph Algorithms Can Be Fast and Scalable" (SPAA'18). It includes implementations of the following parallel graph ...

Abstract: The Graph Coloring Problem (GCP) is concerned with finding the chromatic number, i.e., the minimum number of unique colors required to color adjacent nodes in the graph. Given that ...

Brief: Researchers from the Computing and Computational Sciences Directorate (CCSD) at Oak Ridge National Laboratory (ORNL) have developed a distributed implementation of graph convolutional neural ...

Bayesian Decision Trees provide a probabilistic framework that reduces the instability of Decision Trees while maintaining their explainability. While Markov Chain Monte Carlo methods are typically ...

Graph neural networks have been shown to achieve excellent performance for several crucial tasks in particle physics, such as charged particle tracking, jet tagging, and clustering. An important ...