PyTorch-BigGraph: A Large-scale Graph Embedding System

03/28/2019
by   Adam Lerer, et al.
0

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 PyTorch-BigGraph (PBG), an embedding system that incorporates several modifications to traditional multi-relation 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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/26/2023

HUGE: Huge Unsupervised Graph Embeddings with TPUs

Graphs are a representation of structured data that captures the relatio...
research
06/07/2020

Distributed-Memory Vertex-Centric Network Embedding for Large-Scale Graphs

Network embedding is an important step in many different computations ba...
research
07/03/2019

Graph Embeddings at Scale

Graph embedding is a popular algorithmic approach for creating vector re...
research
06/20/2021

Large-Scale Network Embedding in Apache Spark

Network embedding has been widely used in social recommendation and netw...
research
11/16/2017

(geo)graphs - Complex Networks as a shapefile of nodes and a shapefile of edges for different applications

Spatial dependency and spatial embedding are basic physical properties o...
research
08/27/2020

GOSH: Embedding Big Graphs on Small Hardware

In graph embedding, the connectivity information of a graph is used to r...
research
05/18/2021

OpenGraphGym-MG: Using Reinforcement Learning to Solve Large Graph Optimization Problems on MultiGPU Systems

Large scale graph optimization problems arise in many fields. This paper...

Please sign up or login with your details

Forgot password? Click here to reset