A Comprehensive Study on Large-Scale Graph Training: Benchmarking and Rethinking
This work addresses scalability issues in GNNs for researchers and practitioners, but it is incremental as it builds on existing methods with benchmarking and a new training manner.
The paper tackles the challenge of scaling graph neural networks (GNNs) for large-scale graph training by benchmarking existing methods and proposing a new ensembling approach, achieving improved efficiency and performance as demonstrated through empirical comparisons.
Large-scale graph training is a notoriously challenging problem for graph neural networks (GNNs). Due to the nature of evolving graph structures into the training process, vanilla GNNs usually fail to scale up, limited by the GPU memory space. Up to now, though numerous scalable GNN architectures have been proposed, we still lack a comprehensive survey and fair benchmark of this reservoir to find the rationale for designing scalable GNNs. To this end, we first systematically formulate the representative methods of large-scale graph training into several branches and further establish a fair and consistent benchmark for them by a greedy hyperparameter searching. In addition, regarding efficiency, we theoretically evaluate the time and space complexity of various branches and empirically compare them w.r.t GPU memory usage, throughput, and convergence. Furthermore, We analyze the pros and cons for various branches of scalable GNNs and then present a new ensembling training manner, named EnGCN, to address the existing issues. Our code is available at https://github.com/VITA-Group/Large_Scale_GCN_Benchmarking.