# Can Graph Neural Networks Go "Online"? An Analysis of Pretraining and Inference

arXiv: https://arxiv.org/abs/1905.06018 · HTML: https://mlsanity.com/paper/1905.06018/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 May 2019.

## Built on by (most cited first, 4 of 4)

- [Knowledge-Preserving Incremental Social Event Detection via Heterogeneous GNNs](https://mlsanity.com/paper/2101.08747/) (2021)
- [GNNEvaluator: Evaluating GNN Performance On Unseen Graphs Without Labels](https://mlsanity.com/paper/2310.14586/) (2023)
- [Defending Graph Convolutional Networks against Dynamic Graph Perturbations via Bayesian Self-supervision](https://mlsanity.com/paper/2203.03762/) (2022)
- [Lifelong Learning on Evolving Graphs Under the Constraints of Imbalanced Classes and New Classes](https://mlsanity.com/paper/2112.10558/) (2021)

## Abstract (arXiv)

Large-scale graph data in real-world applications is often not static but dynamic, i. e., new nodes and edges appear over time. Current graph convolution approaches are promising, especially, when all the graph's nodes and edges are available during training. When unseen nodes and edges are inserted after training, it is not yet evaluated whether up-training or re-training from scratch is preferable. We construct an experimental setup, in which we insert previously unseen nodes and edges after training and conduct a limited amount of inference epochs. In this setup, we compare adapting pretrained graph neural networks against retraining from scratch. Our results show that pretrained models yield high accuracy scores on the unseen nodes and that pretraining is preferable over retraining from scratch. Our experiments represent a first step to evaluate and develop truly online variants of graph neural networks.