Enhancing Robustness of Graph Neural Networks through p-Laplacian

TL;DR

This paper introduces pLAPGNN, a computationally efficient framework based on weighted p-Laplacian, to enhance the robustness of Graph Neural Networks against adversarial attacks, demonstrated through empirical evaluation on real datasets.

Contribution

The paper proposes a novel, efficient robustness framework for GNNs using weighted p-Laplacian, addressing limitations of existing methods under strong attacks.

Findings

pLAPGNN improves robustness against adversarial attacks

The method is computationally efficient compared to existing techniques

Empirical results show significant performance gains on real datasets

Abstract

With the increase of data in day-to-day life, businesses and different stakeholders need to analyze the data for better predictions. Traditionally, relational data has been a source of various insights, but with the increase in computational power and the need to understand deeper relationships between entities, the need to design new techniques has arisen. For this graph data analysis has become an extraordinary tool for understanding the data, which reveals more realistic and flexible modelling of complex relationships. Recently, Graph Neural Networks (GNNs) have shown great promise in various applications, such as social network analysis, recommendation systems, drug discovery, and more. However, many adversarial attacks can happen over the data, whether during training (poisoning attack) or during testing (evasion attack), which can adversely manipulate the desired outcome from the GNN model. Therefore, it is crucial to make the GNNs robust to such attacks. The existing robustness methods are computationally demanding and perform poorly when the intensity of attack increases. This paper presents a computationally efficient framework, namely, pLAPGNN, based on weighted p-Laplacian for making GNNs robust. Empirical evaluation on real datasets establishes the efficacy and efficiency of the proposed method.