Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

8-2021

Abstract

Graph neural networks (GNNs) emerge as a powerful family of representation learning models on graphs. To derive node representations, they utilize a global model that recursively aggregates information from the neighboring nodes. However, different nodes reside at different parts of the graph in different local contexts, making their distributions vary across the graph. Ideally, how a node receives its neighborhood information should be a function of its local context, to diverge from the global GNN model shared by all nodes. To utilize node locality without overfitting, we propose a node-wise localization of GNNs by accounting for both global and local aspects of the graph. Globally, all nodes on the graph depend on an underlying global GNN to encode the general patterns across the graph; locally, each node is localized into a unique model as a function of the global model and its local context. Finally, we conduct extensive experiments on four benchmark graphs, and consistently obtain promising performance surpassing the state-of-the-art GNNs.

Keywords

graph neural networks, FiLM, localization

Discipline

Artificial Intelligence and Robotics | Databases and Information Systems

Research Areas

Data Science and Engineering; Intelligent Systems and Optimization

Publication

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence (IJCAI 2021)

First Page

1520

Last Page

1526

ISBN

9780999241196

Identifier

10.24963/ijcai.2021/210

City or Country

Virtual Event, Montreal, Canada

Download

Share

COinS