HG-Adapter: Improving Pre-Trained Heterogeneous Graph Neural Networks with Dual Adapters

TL;DR

This paper introduces HG-Adapter, a framework that enhances pre-trained heterogeneous graph neural networks by using dual adapters and semi-supervised learning techniques to improve generalization and performance on downstream tasks.

Contribution

The paper proposes a novel dual adapter framework with label propagation and self-supervised losses, reducing generalization error and improving HGNN performance.

Findings

Achieves lower generalization error bound than existing methods

Demonstrates superior performance on various downstream tasks

Effectively utilizes unlabeled data to enhance model generalization

Abstract

The "pre-train, prompt-tuning'' paradigm has demonstrated impressive performance for tuning pre-trained heterogeneous graph neural networks (HGNNs) by mitigating the gap between pre-trained models and downstream tasks. However, most prompt-tuning-based works may face at least two limitations: (i) the model may be insufficient to fit the graph structures well as they are generally ignored in the prompt-tuning stage, increasing the training error to decrease the generalization ability; and (ii) the model may suffer from the limited labeled data during the prompt-tuning stage, leading to a large generalization gap between the training error and the test error to further affect the model generalization. To alleviate the above limitations, we first derive the generalization error bound for existing prompt-tuning-based methods, and then propose a unified framework that combines two new adapters with potential labeled data extension to improve the generalization of pre-trained HGNN models. Specifically, we design dual structure-aware adapters to adaptively fit task-related homogeneous and heterogeneous structural information. We further design a label-propagated contrastive loss and two self-supervised losses to optimize dual adapters and incorporate unlabeled nodes as potential labeled data. Theoretical analysis indicates that the proposed method achieves a lower generalization error bound than existing methods, thus obtaining superior generalization ability. Comprehensive experiments demonstrate the effectiveness and generalization of the proposed method on different downstream tasks.