Robust Graph Fine-Tuning with Adversarial Graph Prompting
This addresses robustness issues in graph neural network fine-tuning for downstream tasks, representing an incremental improvement by combining adversarial learning with prompting.
The paper tackles the vulnerability of Parameter-Efficient Fine-Tuning (PEFT) methods for pre-trained GNNs to noise and attacks on graph data, proposing an Adversarial Graph Prompting (AGP) framework that integrates adversarial learning into graph prompting to achieve robust fine-tuning, with extensive experiments validating its effectiveness against state-of-the-art methods.
Parameter-Efficient Fine-Tuning (PEFT) method has emerged as a dominant paradigm for adapting pre-trained GNN models to downstream tasks. However, existing PEFT methods usually exhibit significant vulnerability to various noise and attacks on graph topology and node attributes/features. To address this issue, for the first time, we propose integrating adversarial learning into graph prompting and develop a novel Adversarial Graph Prompting (AGP) framework to achieve robust graph fine-tuning. Our AGP has two key aspects. First, we propose the general problem formulation of AGP as a min-max optimization problem and develop an alternating optimization scheme to solve it. For inner maximization, we propose Joint Projected Gradient Descent (JointPGD) algorithm to generate strong adversarial noise. For outer minimization, we employ a simple yet effective module to learn the optimal node prompts to counteract the adversarial noise. Second, we demonstrate that the proposed AGP can theoretically address both graph topology and node noise. This confirms the versatility and robustness of our AGP fine-tuning method across various graph noise. Note that, the proposed AGP is a general method that can be integrated with various pre-trained GNN models to enhance their robustness on the downstream tasks. Extensive experiments on multiple benchmark tasks validate the robustness and effectiveness of AGP method compared to state-of-the-art methods.