Welcome to BeGin Tutorials and Documentation!
BeGin is an easy and fool-proof framework for graph continual learning. First, BeGin is easily extended since it is modularized with reusable module for data processing, algorithm design, training, validation, and evaluation. Next, BeGin is fool-proof by completely separating the evaluation module from the learning part, where users implement their own graph CL methods, in order to eliminate potential mistakes in evaluation. In addition, BeGin provides 31 benchmark scenarios for graph from 20 real-world datasets, which cover 12 combinations of the incremental settings and the levels of problem. For the details, please refer the contents below.
Contents
Get Started
Datasets
Evaluator
Utils