PREPRINT

Improving Graph Neural Networks at Scale: Combining Approximate PageRank and CoreRank

Ariel R. Ramos Vela, Johannes F. Lutzeyer, Anastasios Giovanidis, Michalis Vazirgiannis

Submitted on 8 November 2022

Abstract

Graph Neural Networks (GNNs) have achieved great successes in many learning tasks performed on graph structures. Nonetheless, to propagate information GNNs rely on a message passing scheme which can become prohibitively expensive when working with industrial-scale graphs. Inspired by the PPRGo model, we propose the CorePPR model, a scalable solution that utilises a learnable convex combination of the approximate personalised PageRank and the CoreRank to diffuse multi-hop neighbourhood information in GNNs. Additionally, we incorporate a dynamic mechanism to select the most influential neighbours for a particular node which reduces training time while preserving the performance of the model. Overall, we demonstrate that CorePPR outperforms PPRGo, particularly on large graphs where selecting the most influential nodes is particularly relevant for scalability. Our code is publicly available at: https://github.com/arielramos97/CorePPR.

Preprint

Comment: Accepted at the "NeurIPS 2022 New Frontiers in Graph Learning Workshop (NeurIPS GLFrontiers 2022)"

Subjects: Computer Science - Machine Learning; Computer Science - Social and Information Networks; Statistics - Machine Learning

URL: http://arxiv.org/abs/2211.04248