Learning Heuristics over Large Graphs via Deep Reinforcement Learning

by   Akash Mittal, et al.
Indian Institute of Technology Delhi
The Regents of the University of California

In this paper, we propose a deep reinforcement learning framework called GCOMB to learn algorithms that can solve combinatorial problems over large graphs. GCOMB mimics the greedy algorithm in the original problem and incrementally constructs a solution. The proposed framework utilizes Graph Convolutional Network (GCN) to generate node embeddings that predicts the potential nodes in the solution set from the entire node set. These embeddings enable an efficient training process to learn the greedy policy via Q-learning. Through extensive evaluation on several real and synthetic datasets containing up to a million nodes, we establish that GCOMB is up to 41 state of the art, up to seven times faster than the greedy algorithm, robust and scalable to large dynamic networks.


page 1

page 2

page 3

page 4


DyGCN: Dynamic Graph Embedding with Graph Convolutional Network

Graph embedding, aiming to learn low-dimensional representations (aka. e...

Graph Convolutional Policy for Solving Tree Decomposition via Reinforcement Learning Heuristics

We propose a Reinforcement Learning based approach to approximately solv...

End-to-end Structure-Aware Convolutional Networks for Knowledge Base Completion

Knowledge graph embedding has been an active research topic for knowledg...

Learning Combinatorial Node Labeling Algorithms

We present a graph neural network to learn graph coloring heuristics usi...

PolicyClusterGCN: Identifying Efficient Clusters for Training Graph Convolutional Networks

Graph convolutional networks (GCNs) have achieved huge success in severa...

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...

SMGRL: A Scalable Multi-resolution Graph Representation Learning Framework

Graph convolutional networks (GCNs) allow us to learn topologically-awar...

Please sign up or login with your details

Forgot password? Click here to reset