A Variational Edge Partition Model for Supervised Graph Representation Learning

TL;DR

This paper introduces a novel generative model for graph structure that partitions edges into overlapping communities, enabling community-specific GNNs and improving supervised graph representation learning.

Contribution

It presents a variational edge partition model that jointly learns edge communities, community-specific GNNs, and a combined classifier, addressing the limitations of traditional GNNs that ignore edge formation.

Findings

Effective in node-level and graph-level classification tasks

Outperforms baseline models on real-world datasets

Demonstrates the importance of modeling edge generation processes

Abstract

Graph neural networks (GNNs), which propagate the node features through the edges and learn how to transform the aggregated features under label supervision, have achieved great success in supervised feature extraction for both node-level and graph-level classification tasks. However, GNNs typically treat the graph structure as given and ignore how the edges are formed. This paper introduces a graph generative process to model how the observed edges are generated by aggregating the node interactions over a set of overlapping node communities, each of which contributes to the edges via a logical OR mechanism. Based on this generative model, we partition each edge into the summation of multiple community-specific weighted edges and use them to define community-specific GNNs. A variational inference framework is proposed to jointly learn a GNN-based inference network that partitions the edges into different communities, these community-specific GNNs, and a GNN-based predictor that combines community-specific GNNs for the end classification task. Extensive evaluations on real-world graph datasets have verified the effectiveness of the proposed method in learning discriminative representations for both node-level and graph-level classification tasks.