Anomaly-resistant Graph Neural Networks via Neural Architecture Search
This addresses a specific robustness issue in GNNs for graph-based applications, but it is incremental as it builds on existing methods.
The paper tackles the vulnerability of Graph Neural Networks (GNNs) to abnormal nodes in neighborhoods by proposing NASAR-GNN, which uses Neural Architecture Search to automatically exclude such nodes from information aggregation, showing effectiveness in experiments on real-world datasets.
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.