# Pre-train and Learn: Preserve Global Information for Graph Neural Networks

arXiv: https://arxiv.org/abs/1910.12241 · HTML: https://mlsanity.com/paper/1910.12241/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Oct 2019.

## Built on by (most cited first, 8 of 8)

- [Local Augmentation for Graph Neural Networks](https://mlsanity.com/paper/2109.03856/) (2021)
- [ProxyBO: Accelerating Neural Architecture Search via Bayesian Optimization with Zero-cost Proxies](https://mlsanity.com/paper/2110.10423/) (2021)
- [Graph Masked Autoencoders with Transformers](https://mlsanity.com/paper/2202.08391/) (2022)
- [Does Graph Prompt Work? A Data Operation Perspective with Theoretical Analysis](https://mlsanity.com/paper/2410.01635/) (2024)
- [DivBO: Diversity-aware CASH for Ensemble Learning](https://mlsanity.com/paper/2302.03255/) (2023)
- [G-Signatures: Global Graph Propagation With Randomized Signatures](https://mlsanity.com/paper/2302.08811/) (2023)
- [Rover: An online Spark SQL tuning service via generalized transfer learning](https://mlsanity.com/paper/2302.04046/) (2023)
- [CROP: Integrating Topological and Spatial Structures via Cross-View Prefixes for Molecular LLMs](https://mlsanity.com/paper/2508.06917/) (2025)

## Abstract (arXiv)

Graph neural networks (GNNs) have shown great power in learning on attributed graphs. However, it is still a challenge for GNNs to utilize information faraway from the source node. Moreover, general GNNs require graph attributes as input, so they cannot be appled to plain graphs. In the paper, we propose new models named G-GNNs (Global information for GNNs) to address the above limitations. First, the global structure and attribute features for each node are obtained via unsupervised pre-training, which preserve the global information associated to the node. Then, using the global features and the raw network attributes, we propose a parallel framework of GNNs to learn different aspects from these features. The proposed learning methods can be applied to both plain graphs and attributed graphs. Extensive experiments have shown that G-GNNs can outperform other state-of-the-art models on three standard evaluation graphs. Specially, our methods establish new benchmark records on Cora (84.31%) and Pubmed (80.95%) when learning on attributed graphs.