Python is a widely used high-level, general-purpose, interpreted, dynamic programming language.[24][25] Its design philosophy emphasizes code readability, and its syntax allows programmers to express concepts in fewer lines of code than possible in languages such as C++ or Java.[26][27] The language provides constructs intended to enable writing clear programs on both a small and large scale.[28]

Python supports multiple programming paradigms, including object-oriented, imperative and functional programming or procedural styles. It features a dynamic type system and automatic memory management and has a large and comprehensive standard library.[29]

Python interpreters are available for many operating systems, allowing Python code to run on a wide variety of systems. Using third-party tools, such as Py2exe or Pyinstaller,[30] Python code can be packaged into stand-alone executable programs for some of the most popular operating systems, so Python-based software can be distributed to, and used on, those environments with no need to install a Python interpreter.

CPython, the reference implementation of Python, is free and open-source software and has a community-based development model, as do nearly all of its variant implementations. CPython is managed by the non-profit Python Software Foundation.


Using GraphSage for node predictions

Purpose of this article is to show that the 'subject' of each paper in the Cora graph can be predicted on the basis of the graph structure together with whatever features are additionally available on the nodes.

Using Laplacians for graph learning

How the Laplacian of a graph can be used for node predictions.

Community detection using NetworkX

Analysis and visualization of communities via NetworkX.

NetworkX: the essential API

NetworkX is the Python graph API you need to understand prior to venturing into graph learning. This is an overview of the essential methods.

Graph attention networks

How the attention mechanism can be applied to graph learning.

The Cora dataset

About a dataset we use over and over again in different graph learning articles.

Node2Vec with weighted random walks

This notebook illustrates how Node2Vec can be applied to learn low dimensional node embeddings of an edge weighted graph through weighted biased random walks over the graph.

Graph Link Prediction using GraphSAGE

Explains how a graph learning task can be turned into a standard machine learning task.

Node2Vec embedding

Embedding of nodes happens via word2vec by means of a smart trick: using randomg walks over the graph to generate 'word' sequences.


It is a common misconception that AI is absolutely objective, since AI is objective only in the sense of learning what human teaches.