
GIST: Distributed Training for LargeScale Graph Convolutional Networks
The graph convolutional network (GCN) is a goto solution for machine le...
read it

CommunicationEfficient Sampling for Distributed Training of Graph Convolutional Networks
Training Graph Convolutional Networks (GCNs) is expensive as it needs to...
read it

Geometric graphs from data to aid classification tasks with graph convolutional networks
Classification is a classic problem in data analytics and has been appro...
read it

Fast and Robust Distributed Subgraph Enumeration
We study the classic subgraph enumeration problem under distributed sett...
read it

Experiments with graph convolutional networks for solving the vertex pcenter problem
In the last few years, graph convolutional networks (GCN) have become a ...
read it

DRONE: a Distributed gRaph cOmputiNg Engine
Nowadays, in big data era, social networks, graph database, knowledge gr...
read it

Jointly learning relevant subgraph patterns and nonlinear models of their indicators
Classification and regression in which the inputs are graphs of arbitrar...
read it
Distributed Training of Graph Convolutional Networks using Subgraph Approximation
Modern machine learning techniques are successfully being adapted to data modeled as graphs. However, many realworld graphs are typically very large and do not fit in memory, often making the problem of training machine learning models on them intractable. Distributed training has been successfully employed to alleviate memory problems and speed up training in machine learning domains in which the input data is assumed to be independently identical distributed (i.i.d). However, distributing the training of non i.i.d data such as graphs that are used as training inputs in Graph Convolutional Networks (GCNs) causes accuracy problems since information is lost at the graph partitioning boundaries. In this paper, we propose a training strategy that mitigates the lost information across multiple partitions of a graph through a subgraph approximation scheme. Our proposed approach augments each subgraph with a small amount of edge and vertex information that is approximated from all other subgraphs. The subgraph approximation approach helps the distributed training system converge at singlemachine accuracy, while keeping the memory footprint low and minimizing synchronization overhead between the machines.
READ FULL TEXT
Comments
There are no comments yet.