Post-Hoc Robustness Enhancement in Graph Neural Networks with Conditional Random Fields

TL;DR

This paper proposes RobustCRF, a post-hoc, model-agnostic method using Conditional Random Fields to improve the robustness of Graph Neural Networks during inference, addressing a gap in existing defense strategies.

Contribution

Introduction of RobustCRF, a novel post-hoc inference technique employing CRFs to enhance GNN robustness without needing model architecture details.

Findings

RobustCRF improves GNN robustness against adversarial attacks.

The method is effective across different GNN architectures.

Validation on benchmark datasets shows significant robustness gains.

Abstract

Graph Neural Networks (GNNs), which are nowadays the benchmark approach in graph representation learning, have been shown to be vulnerable to adversarial attacks, raising concerns about their real-world applicability. While existing defense techniques primarily concentrate on the training phase of GNNs, involving adjustments to message passing architectures or pre-processing methods, there is a noticeable gap in methods focusing on increasing robustness during inference. In this context, this study introduces RobustCRF, a post-hoc approach aiming to enhance the robustness of GNNs at the inference stage. Our proposed method, founded on statistical relational learning using a Conditional Random Field, is model-agnostic and does not require prior knowledge about the underlying model architecture. We validate the efficacy of this approach across various models, leveraging benchmark node classification datasets.