Anomaly-resistant Graph Neural Networks via Neural Architecture Search

TL;DR

This paper introduces NASAR-GNN, a neural architecture search-based method that enhances graph neural networks' robustness by identifying and excluding abnormal nodes during message passing, improving performance on real-world datasets.

Contribution

The paper proposes a novel NAS-based algorithm that automatically detects and excludes anomalous nodes in GNNs, improving their robustness against abnormal neighborhood nodes.

Findings

NASAR-GNN effectively identifies abnormal nodes.

Improves GNN performance on real-world datasets.

Demonstrates robustness against neighborhood anomalies.

Abstract

In general, Graph Neural Networks(GNN) have been using a message passing method to aggregate and summarize information about neighbors to express their information. Nonetheless, previous studies have shown that the performance of graph neural networks becomes vulnerable when there are abnormal nodes in the neighborhood due to this message passing method. In this paper, inspired by the Neural Architecture Search method, we present an algorithm that recognizes abnormal nodes and automatically excludes them from information aggregation. Experiments on various real worlds datasets show that our proposed Neural Architecture Search-based Anomaly Resistance Graph Neural Network (NASAR-GNN) is actually effective.