Can graph neural networks go „online“? An analysis of pretraining and inference
Galke, L., Vagliano, I., & Scherp, A.
Can graph neural networks go „online“? An analysis of pretraining and inference. In Proceedings of the Representation Learning on Graphs and Manifolds: ICLR2019 Workshop
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 dur-
ing 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.