Proceedings

Node-wise Localization of Graph Neural Networks

Zemin Liu, Yuan Fang, Chenghao Liu, Steven C.H. Hoi

Download BibTeX Cite

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. Main Track. Pages 1520-1526.

https://doi.org/10.24963/ijcai.2021/210

Keywords

  • Data Mining: Mining Graphs, Semi Structured Data, Complex Data

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.

Zemin Liu, Yuan Fang, Chenghao Liu, and Steven C. H. Hoi. 2021. Node-wise Localization of Graph Neural Networks. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21. IJCAI, 1520–1526. https://doi.org/10.24963/ijcai.2021/210
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards