Timezone: »

 
Poster
A Comprehensive Study on Large-Scale Graph Training: Benchmarking and Rethinking
Keyu Duan · Zirui Liu · Peihao Wang · Wenqing Zheng · Kaixiong Zhou · Tianlong Chen · Xia Hu · Zhangyang Wang

Tue Nov 29 09:00 AM -- 11:00 AM (PST) @ Hall J #1010

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. Remarkably, our proposed method has achieved new state-of-the-art (SOTA) performance on large-scale datasets. Our code is available at https://github.com/VITA-Group/LargeScaleGCN_Benchmarking.

Author Information

Keyu Duan (National University of Singapore)
Zirui Liu (Rice University)
Peihao Wang (University of Texas at Austin)
Wenqing Zheng (the University of Texas at Austin)
Kaixiong Zhou (Rice University)
Tianlong Chen (Unversity of Texas at Austin)
Xia Hu (Texas A&M)
Zhangyang Wang (University of Texas at Austin)

More from the Same Authors