Alternately Optimized Graph Neural Networks

TL;DR

This paper introduces an alternating optimization framework for Graph Neural Networks that enhances computational efficiency and memory usage while maintaining or improving classification performance.

Contribution

It proposes a novel alternating optimization approach for GNN training, addressing efficiency issues in existing end-to-end methods.

Findings

Achieves comparable or better accuracy than state-of-the-art methods.

Significantly reduces computation time and memory consumption.

Demonstrates effectiveness on semi-supervised node classification tasks.

Abstract

Graph Neural Networks (GNNs) have greatly advanced the semi-supervised node classification task on graphs. The majority of existing GNNs are trained in an end-to-end manner that can be viewed as tackling a bi-level optimization problem. This process is often inefficient in computation and memory usage. In this work, we propose a new optimization framework for semi-supervised learning on graphs. The proposed framework can be conveniently solved by the alternating optimization algorithms, resulting in significantly improved efficiency. Extensive experiments demonstrate that the proposed method can achieve comparable or better performance with state-of-the-art baselines while it has significantly better computation and memory efficiency.