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

Published in Representation Learning on Graphs and Manifolds, ICLR Workshop, 2019

Recommended citation: Lukas Galke, Iacopo Vagliano, Ansgar Scherp, "Can Graph Neural Networks Go `Online`? An Analysis of Pretraining and Inference." Representation Learning on Graphs and Manifolds, ICLR Workshop, 2019. https://rlgm.github.io/papers/21.pdf

Download paper here

Code is available here

Abstract: 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.