GOSH: Embedding Big Graphs on Small Hardware

08/27/2020
by   Taha Atahan Akyildiz, et al.
0

In graph embedding, the connectivity information of a graph is used to represent each vertex as a point in a d-dimensional space. Unlike the original, irregular structural information, such a representation can be used for a multitude of machine learning tasks. Although the process is extremely useful in practice, it is indeed expensive and unfortunately, the graphs are becoming larger and harder to embed. Attempts at scaling up the process to larger graphs have been successful but often at a steep price in hardware requirements. We present GOSH, an approach for embedding graphs of arbitrary sizes on a single GPU with minimum constraints. GOSH utilizes a novel graph coarsening approach to compress the graph and minimize the work required for embedding, delivering high-quality embeddings at a fraction of the time compared to the state-of-the-art. In addition to this, it incorporates a decomposition schema that enables any arbitrarily large graph to be embedded using a single GPU with minimum constraints on the memory size. With these techniques, GOSH is able to embed a graph with over 65 million vertices and 1.8 billion edges in less than an hour on a single GPU and obtains a 93 be increased to 95

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/19/2021

Boosting Graph Embedding on a Single GPU

Graphs are ubiquitous, and they can model unique characteristics and com...
research
03/28/2019

PyTorch-BigGraph: A Large-scale Graph Embedding System

Graph embedding methods produce unsupervised node features from graphs t...
research
10/13/2021

Scalable Graph Embedding LearningOn A Single GPU

Graph embedding techniques have attracted growing interest since they co...
research
07/01/2022

Time-aware Dynamic Graph Embedding for Asynchronous Structural Evolution

Dynamic graphs refer to graphs whose structure dynamically changes over ...
research
01/20/2021

Marius: Learning Massive Graph Embeddings on a Single Machine

We propose a new framework for computing the embeddings of large-scale g...
research
03/08/2018

Concise Fuzzy Representation of Big Graphs: a Dimensionality Reduction Approach

The enormous amount of data to be represented using large graphs exceeds...
research
02/04/2013

Centrality-constrained graph embedding

Visual rendering of graphs is a key task in the mapping of complex netwo...

Please sign up or login with your details

Forgot password? Click here to reset