Robust Graph Neural Networks using Weighted Graph Laplacian

TL;DR

This paper introduces Weighted Laplacian GNN (RWL-GNN), a scalable and efficient framework that enhances the robustness of graph neural networks against noise and adversarial attacks by leveraging Laplacian learning.

Contribution

The paper proposes a novel, unified optimization framework that integrates Weighted Graph Laplacian learning with GNNs to improve robustness and scalability.

Findings

Enhanced robustness against adversarial attacks.

Improved accuracy on benchmark datasets.

Reduced computational complexity.

Abstract

Graph neural network (GNN) is achieving remarkable performances in a variety of application domains. However, GNN is vulnerable to noise and adversarial attacks in input data. Making GNN robust against noises and adversarial attacks is an important problem. The existing defense methods for GNNs are computationally demanding and are not scalable. In this paper, we propose a generic framework for robustifying GNN known as Weighted Laplacian GNN (RWL-GNN). The method combines Weighted Graph Laplacian learning with the GNN implementation. The proposed method benefits from the positive semi-definiteness property of Laplacian matrix, feature smoothness, and latent features via formulating a unified optimization framework, which ensures the adversarial/noisy edges are discarded and connections in the graph are appropriately weighted. For demonstration, the experiments are conducted with Graph convolutional neural network(GCNN) architecture, however, the proposed framework is easily amenable to any existing GNN architecture. The simulation results with benchmark dataset establish the efficacy of the proposed method, both in accuracy and computational efficiency. Code can be accessed at https://github.com/Bharat-Runwal/RWL-GNN.