Abstract | ||
---|---|---|
Graph Neural Networks (GNN) is an emerging field for learning on non-Euclidean data. Recently, there has been increased interest in designing GNN that scales to large graphs. Most existing methods use "graph sampling" or "layer-wise sampling" techniques to reduce training time. However, these methods still suffer from degrading performance and scalability problems when applying to graphs with billions of edges. This paper presents GBP, a scalable GNN that utilizes a localized bidirectional propagation process from both the feature vectors and the training/testing nodes. Theoretical analysis shows that GBP is the first method that achieves sub-linear time complexity for both the precomputation and the training phases. An extensive empirical study demonstrates that GBP achieves state-of-the-art performance with significantly less training/testing time. Most notably, GBP can deliver superior performance on a graph with over 60 million nodes and 1.8 billion edges in less than half an hour on a single machine. |
Year | Venue | DocType |
---|---|---|
2020 | NIPS 2020 | Conference |
Volume | Citations | PageRank |
33 | 0 | 0.34 |
References | Authors | |
0 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ming Chen | 1 | 4 | 0.72 |
Zhewei Wei | 2 | 215 | 20.07 |
Bolin Ding | 3 | 1578 | 85.48 |
yaliang li | 4 | 629 | 50.87 |
Ye Yuan | 5 | 117 | 24.40 |
Xiaoyong Du | 6 | 882 | 123.29 |
Ji-Rong Wen | 7 | 4431 | 265.98 |