Publication: An Untrained Neural Model for Fast and Accurate Graph Classification

22 September 2023

Recent works have proven the feasibility of fast and accurate time series classification methods based on randomized convolutional kernels. Concerning graph-structured data, the majority of randomized graph neural networks are based on the Echo State Network paradigm in which single layers or the whole network present some form of recurrence.

In this work, EMERGE partners from the University of Pisa explore a simple form of a randomized graph neural network inspired by the success of randomized convolutions in the 1-dimensional domain. They implement a no-frills convolutional graph neural network and leave its weights untrained. Then, they aggregate the node representations with global pooling operators, obtaining an untrained graph-level representation. Since there is no training involved, computing such representation is extremely fast.

They then apply a fast linear classifier to the obtained representations, opting for LS-SVM since it is among the fastest classifiers available. They show that such a simple approach can obtain competitive predictive performance while being extremely efficient both at training and inference time.

Read the paper: https://doi.org/10.1007/978-3-031-44216-2_23

Access EMERGE publications in the link below.