Perseus: Leveraging Common Data Patterns with Curriculum Learning for More Robust Graph Neural Networks

TL;DR

Perseus introduces a curriculum learning-based defense for GNNs that adaptively focuses on common data patterns to improve robustness against adversarial attacks without relying on preprocessing.

Contribution

It proposes a novel adversarial defense method for GNNs using curriculum learning to better handle adversarial perturbations and preserve valuable graph information.

Findings

Models with Perseus outperform baselines in robustness.

Perseus effectively mitigates adversarial attack impacts.

Enhanced graph structure learning through curriculum strategy.

Abstract

Graph Neural Networks (GNNs) excel at handling graph data but remain vulnerable to adversarial attacks. Existing defense methods typically rely on assumptions like graph sparsity and homophily to either preprocess the graph or guide structure learning. However, preprocessing methods often struggle to accurately distinguish between normal edges and adversarial perturbations, leading to suboptimal results due to the loss of valuable edge information. Robust graph neural network models train directly on graph data affected by adversarial perturbations, without preprocessing. This can cause the model to get stuck in poor local optima, negatively affecting its performance. To address these challenges, we propose Perseus, a novel adversarial defense method based on curriculum learning. Perseus assesses edge difficulty using global homophily and applies a curriculum learning strategy to adjust the learning order, guiding the model to learn the full graph structure while adaptively focusing on common data patterns. This approach mitigates the impact of adversarial perturbations. Experiments show that models trained with Perseus achieve superior performance and are significantly more robust to adversarial attacks.