CopulaGNN: Towards Integrating Representational and Correlational Roles of Graphs in Graph Neural Networks

Jiaqi Ma, Bo Chang, Xuefei Zhang, Qiaozhu Mei

Keywords: Graph Neural Network, Gaussian Copula, Gaussian Graphical Model

Abstract: Graph-structured data are ubiquitous. However, graphs encode diverse types of information and thus play different roles in data representation. In this paper, we distinguish the \textit{representational} and the \textit{correlational} roles played by the graphs in node-level prediction tasks, and we investigate how Graph Neural Network (GNN) models can effectively leverage both types of information. Conceptually, the representational information provides guidance for the model to construct better node features; while the correlational information indicates the correlation between node outcomes conditional on node features. Through a simulation study, we find that many popular GNN models are incapable of effectively utilizing the correlational information. By leveraging the idea of the copula, a principled way to describe the dependence among multivariate random variables, we offer a general solution. The proposed Copula Graph Neural Network (CopulaGNN) can take a wide range of GNN models as base models and utilize both representational and correlational information stored in the graphs. Experimental results on two types of regression tasks verify the effectiveness of the proposed method.

One-sentence Summary: We distinguish the representational and the correlational information encoded by the graphs in node-level prediction tasks, and propose a novel Copula Graph Neural Network to effectively leverage both information.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Code: [ jiaqima/CopulaGNN](https://github.com/jiaqima/CopulaGNN) + [ 1 community implementation](https://paperswithcode.com/paper/?openreview=XI-OJ5yyse)

Data: [Wiki Squirrel](https://paperswithcode.com/dataset/wiki-squirrel)