Graph Sanitation with Application to Node Classification

TL;DR

This paper introduces the graph sanitation problem, aiming to improve initial graphs for better node classification, and proposes a bilevel optimization approach with a solver that enhances classification accuracy across various models and scenarios.

Contribution

It formulates the novel graph sanitation problem as a bilevel optimization task and provides an effective solver, GaSoliNe, for improving graph quality for node classification.

Findings

Up to 25% performance improvement over existing methods.

Broad applicability across different GNN models.

Effective in various perturbation scenarios.

Abstract

The past decades have witnessed the prosperity of graph mining, with a multitude of sophisticated models and algorithms designed for various mining tasks, such as ranking, classification, clustering and anomaly detection. Generally speaking, the vast majority of the existing works aim to answer the following question, that is, given a graph, what is the best way to mine it? In this paper, we introduce the graph sanitation problem, to answer an orthogonal question. That is, given a mining task and an initial graph, what is the best way to improve the initially provided graph? By learning a better graph as part of the input of the mining model, it is expected to benefit graph mining in a variety of settings, ranging from denoising, imputation to defense. We formulate the graph sanitation problem as a bilevel optimization problem, and further instantiate it by semi-supervised node classification, together with an effective solver named GaSoliNe. Extensive experimental results demonstrate that the proposed method is (1) broadly applicable with respect to different graph neural network models and flexible graph modification strategies, (2) effective in improving the node classification accuracy on both the original and contaminated graphs in various perturbation scenarios. In particular, it brings up to 25% performance improvement over the existing robust graph neural network methods.