swMATH ID: 
34086

Software Authors: 
Adam Lerer, Ledell Wu, Jiajun Shen, Timothee Lacroix, Luca Wehrstedt, Abhijit Bose, Alex Peysakhovich

Description: 
PyTorchBigGraph: A Largescale Graph Embedding System. Graph embedding methods produce unsupervised node features from graphs that can then be used for a variety of machine learning tasks. Modern graphs, particularly in industrial applications, contain billions of nodes and trillions of edges, which exceeds the capability of existing embedding systems. We present PyTorchBigGraph (PBG), an embedding system that incorporates several modifications to traditional multirelation embedding systems that allow it to scale to graphs with billions of nodes and trillions of edges. PBG uses graph partitioning to train arbitrarily large embeddings on either a single machine or in a distributed environment. We demonstrate comparable performance with existing embedding systems on common benchmarks, while allowing for scaling to arbitrarily large graphs and parallelization on multiple machines. We train and evaluate embeddings on several large social network graphs as well as the full Freebase dataset, which contains over 100 million nodes and 2 billion edges. 
Homepage: 
https://arxiv.org/abs/1903.12287

Source Code: 
https://github.com/facebookresearch/PyTorchBigGraph

Related Software: 
PyTorch;
Python;
DGLKE;
GraphVite;
Pykg2vec;
OpenKE;
AmpliGraph;
BioKEEN;
PyKEEN;
AutoKeras;
LightGBM;
NetLSD;
AutoNE;
DGL;
EigenGNN;
AliGraph;
autosklearn;
AutoGL;
LibKGE;
Scikit

Cited in: 
2 Publications
