RW-NSGCN: A Robust Approach to Structural Attacks via Negative Sampling

TL;DR

RW-NSGCN is a novel GNN model that enhances robustness against topological attacks and weight disturbances by integrating random walk-based negative sampling and DPP-based convolution, leading to improved accuracy and stability.

Contribution

The paper introduces RW-NSGCN, combining RWR, PGR, and DPP techniques for robust node classification under network attacks, a novel integration in GNNs.

Findings

Outperforms existing methods in accuracy under attack scenarios

Effectively mitigates impact of topological perturbations

Demonstrates increased stability and anomaly detection capability

Abstract

Node classification using Graph Neural Networks (GNNs) has been widely applied in various practical scenarios, such as predicting user interests and detecting communities in social networks. However, recent studies have shown that graph-structured networks often contain potential noise and attacks, in the form of topological perturbations and weight disturbances, which can lead to decreased classification performance in GNNs. To improve the robustness of the model, we propose a novel method: Random Walk Negative Sampling Graph Convolutional Network (RW-NSGCN). Specifically, RW-NSGCN integrates the Random Walk with Restart (RWR) and PageRank (PGR) algorithms for negative sampling and employs a Determinantal Point Process (DPP)-based GCN for convolution operations. RWR leverages both global and local information to manage noise and local variations, while PGR assesses node importance to stabilize the topological structure. The DPP-based GCN ensures diversity among negative samples and aggregates their features to produce robust node embeddings, thereby improving classification performance. Experimental results demonstrate that the RW-NSGCN model effectively addresses network topology attacks and weight instability, increasing the accuracy of anomaly detection and overall stability. In terms of classification accuracy, RW-NSGCN significantly outperforms existing methods, showing greater resilience across various scenarios and effectively mitigating the impact of such vulnerabilities.