Deep Generative Models for Subgraph Prediction

TL;DR

This paper introduces a novel subgraph query task in graph neural networks, utilizing a variational graph auto-encoder to jointly predict subgraph components, with inference methods that outperform baseline models across multiple datasets.

Contribution

It proposes a new subgraph query task for deep graph learning and develops a probabilistic VGAE model with inference techniques for zero-shot subgraph prediction.

Findings

Inference methods outperform independent baselines in AUC scores.

Joint prediction of subgraph components improves accuracy.

Model generalizes well across six benchmark datasets.

Abstract

Graph Neural Networks (GNNs) are important across different domains, such as social network analysis and recommendation systems, due to their ability to model complex relational data. This paper introduces subgraph queries as a new task for deep graph learning. Unlike traditional graph prediction tasks that focus on individual components like link prediction or node classification, subgraph queries jointly predict the components of a target subgraph based on evidence that is represented by an observed subgraph. For instance, a subgraph query can predict a set of target links and/or node labels. To answer subgraph queries, we utilize a probabilistic deep Graph Generative Model. Specifically, we inductively train a Variational Graph Auto-Encoder (VGAE) model, augmented to represent a joint distribution over links, node features and labels. Bayesian optimization is used to tune a weighting for the relative importance of links, node features and labels in a specific domain. We describe a deterministic and a sampling-based inference method for estimating subgraph probabilities from the VGAE generative graph distribution, without retraining, in zero-shot fashion. For evaluation, we apply the inference methods on a range of subgraph queries on six benchmark datasets. We find that inference from a model achieves superior predictive performance, surpassing independent prediction baselines with improvements in AUC scores ranging from 0.06 to 0.2 points, depending on the dataset.