A Distributed Training Architecture For Combinatorial Optimization

TL;DR

This paper introduces a distributed GNN training framework for large-scale combinatorial optimization, enabling scalable, efficient, and accurate solutions on complex graphs by partitioning data and employing reinforcement learning.

Contribution

It proposes a novel distributed training architecture for GNNs that improves scalability and accuracy in solving large combinatorial optimization problems.

Findings

Outperforms state-of-the-art methods in solution quality

Demonstrates superior computational efficiency

Validates scalability on large graph datasets

Abstract

In recent years, graph neural networks (GNNs) have been widely applied in tackling combinatorial optimization problems. However, existing methods still suffer from limited accuracy when addressing that on complex graphs and exhibit poor scalability, since full training requires loading the whole adjacent matrix and all embeddings at a time, the it may results in out of memory of a single machine. This limitation significantly restricts their applicability to large-scale scenarios. To address these challenges, we propose a distributed GNN-based training framework for combinatorial optimization. In details, firstly, large graph is partition into several small subgraphs. Then the individual subgraphs are full trained, providing a foundation for efficient local optimization. Finally, reinforcement learning (RL) are employed to take actions according to GNN output, to make sure the restrictions between cross nodes can be learned. Extensive experiments are conducted on both real large-scale social network datasets (e.g., Facebook, Youtube) and synthetically generated high-complexity graphs, which demonstrate that our framework outperforms state-of-the-art approaches in both solution quality and computational efficiency. Moreover, the experiments on large graph instances also validate the scalability of the model.