
Combinatorial Optimization with Graph Convolutional Networks and Guided Tree Search
We present a learningbased approach to computing solutions for certain ...
read it

QDGCN: QueryDriven Graph Convolutional Networks for Attributed Community Search
Recently, attributed community search, a related but different problem t...
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

Explainable, Stable, and Scalable Graph Convolutional Networks for Learning Graph Representation
The network embedding problem that maps nodes in a graph to vectors in E...
read it

An Efficient Graph Convolutional Network Technique for the Travelling Salesman Problem
This paper introduces a new learningbased approach for approximately so...
read it

Distributed Training of Graph Convolutional Networks using Subgraph Approximation
Modern machine learning techniques are successfully being adapted to dat...
read it

All Graphs Lead to Rome: Learning Geometric and CycleConsistent Representations with Graph Convolutional Networks
Image feature matching is a fundamental part of many geometric computer ...
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 popular research direction in the machine learning community to tackle NPhard combinatorial optimization problems (COPs) defined on graphs. While the obtained results are usually still not competitive with problemspecific solution approaches from the operations research community, GCNs often lead to improvements compared to previous machine learning approaches for classical COPs such as the traveling salesperson problem (TSP). In this work we present a preliminary study on using GCNs for solving the vertex pcenter problem (PCP), which is another classic COP on graphs. In particular, we investigate whether a successful model based on endtoend training for the TSP can be adapted to a PCP, which is defined on a similar 2D Euclidean graph input as the usually used version of the TSP. However, the objective of the PCP has a minmax structure which could lead to many symmetric optimal, i.e., groundtruth solutions and other potential difficulties for learning. Our obtained preliminary results show that indeed a direct transfer of network architecture ideas does not seem to work too well. Thus we think that the PCP could be an interesting benchmark problem for new ideas and developments in the area of GCNs.
READ FULL TEXT
Comments
There are no comments yet.