Alternately Optimized Graph Neural Networks
This addresses computational bottlenecks for researchers and practitioners using GNNs, though it is incremental as it builds on existing optimization methods.
The paper tackles the inefficiency of end-to-end training in Graph Neural Networks for semi-supervised node classification by proposing an alternating optimization framework, achieving comparable or better performance with significantly improved computation and memory efficiency.
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.