GraphPrompter: Multi-stage Adaptive Prompt Optimization for Graph In-Context Learning

TL;DR

GraphPrompter introduces a multi-stage adaptive prompt optimization framework that significantly improves graph in-context learning by reducing noise, selecting relevant prompts, and enhancing generalization, outperforming existing methods.

Contribution

The paper proposes a novel multi-stage adaptive prompt optimization method for graph in-context learning, including prompt generation, selection, and augmentation strategies.

Findings

Outperforms state-of-the-art baselines by over 8% on average.

Effectively reduces noise in graph prompts through a reconstruction layer.

Enhances generalization to new datasets with a cache replacement strategy.

Abstract

Graph In-Context Learning, with the ability to adapt pre-trained graph models to novel and diverse downstream graphs without updating any parameters, has gained much attention in the community. The key to graph in-context learning is to perform downstream graphs conditioned on chosen prompt examples. Existing methods randomly select subgraphs or edges as prompts, leading to noisy graph prompts and inferior model performance. Additionally, due to the gap between pre-training and testing graphs, when the number of classes in the testing graphs is much greater than that in the training, the in-context learning ability will also significantly deteriorate. To tackle the aforementioned challenges, we develop a multi-stage adaptive prompt optimization method GraphPrompter, which optimizes the entire process of generating, selecting, and using graph prompts for better in-context learning capabilities. Firstly, Prompt Generator introduces a reconstruction layer to highlight the most informative edges and reduce irrelevant noise for graph prompt construction. Furthermore, in the selection stage, Prompt Selector employs the $k$-nearest neighbors algorithm and pre-trained selection layers to dynamically choose appropriate samples and minimize the influence of irrelevant prompts. Finally, we leverage a Prompt Augmenter with a cache replacement strategy to enhance the generalization capability of the pre-trained model on new datasets. Extensive experiments show that GraphPrompter effectively enhances the in-context learning ability of graph models. On average across all the settings, our approach surpasses the state-of-the-art baselines by over 8%. Our code is released at https://github.com/karin0018/GraphPrompter.