
GraphZoom: A multilevel spectral approach for accurate and scalable graph embedding
Graph embedding techniques have been increasingly deployed in a multitud...
read it

PyTorchBigGraph: A Largescale Graph Embedding System
Graph embedding methods produce unsupervised node features from graphs t...
read it

Parallel Computation of Graph Embeddings
Graph embedding aims at learning a vectorbased representation of vertic...
read it

Scalable Graph Embedding LearningOn A Single GPU
Graph embedding techniques have attracted growing interest since they co...
read it

DistributedMemory VertexCentric Network Embedding for LargeScale Graphs
Network embedding is an important step in many different computations ba...
read it

COSINE: Compressive Network Embedding on Largescale Information Networks
There is recently a surge in approaches that learn lowdimensional embed...
read it

OpenGraphGymMG: Using Reinforcement Learning to Solve Large Graph Optimization Problems on MultiGPU Systems
Large scale graph optimization problems arise in many fields. This paper...
read it
MILE: A MultiLevel Framework for Scalable Graph Embedding
Recently there has been a surge of interest in designing graph embedding methods. Few, if any, can scale to a largesized graph with millions of nodes due to both computational complexity and memory requirements. In this paper, we relax this limitation by introducing the MultILevel Embedding (MILE) framework  a generic methodology allowing contemporary graph embedding methods to scale to large graphs. MILE repeatedly coarsens the graph into smaller ones using a hybrid matching technique to maintain the backbone structure of the graph. It then applies existing embedding methods on the coarsest graph and refines the embeddings to the original graph through a novel graph convolution neural network that it learns. The proposed MILE framework is agnostic to the underlying graph embedding techniques and can be applied to many existing graph embedding methods without modifying them. We employ our framework on several popular graph embedding techniques and conduct embedding for realworld graphs. Experimental results on five largescale datasets demonstrate that MILE significantly boosts the speed (order of magnitude) of graph embedding while also often generating embeddings of better quality for the task of node classification. MILE can comfortably scale to a graph with 9 million nodes and 40 million edges, on which existing methods run out of memory or take too long to compute on a modern workstation.
READ FULL TEXT
Comments
There are no comments yet.