GraphLoRA: Structure-Aware Contrastive Low-Rank Adaptation for Cross-Graph Transfer Learning

TL;DR

GraphLoRA introduces a structure-aware, parameter-efficient transfer learning method for GNNs that aligns feature distributions and adapts structural differences across diverse graph domains, improving transferability with minimal parameter tuning.

Contribution

The paper proposes GraphLoRA, a novel low-rank adaptation approach incorporating structure-aware alignment and regularization for effective cross-graph transfer learning of GNNs.

Findings

Outperforms 14 baselines on 8 real-world datasets

Only 20% of parameters need tuning for effective transfer

Effectively bridges structural and feature distribution gaps

Abstract

Graph Neural Networks (GNNs) have demonstrated remarkable proficiency in handling a range of graph analytical tasks across various domains, such as e-commerce and social networks. Despite their versatility, GNNs face significant challenges in transferability, limiting their utility in real-world applications. Existing research in GNN transfer learning overlooks discrepancies in distribution among various graph datasets, facing challenges when transferring across different distributions. How to effectively adopt a well-trained GNN to new graphs with varying feature and structural distributions remains an under-explored problem. Taking inspiration from the success of Low-Rank Adaptation (LoRA) in adapting large language models to various domains, we propose GraphLoRA, an effective and parameter-efficient method for transferring well-trained GNNs to diverse graph domains. Specifically, we first propose a Structure-aware Maximum Mean Discrepancy (SMMD) to align divergent node feature distributions across source and target graphs. Moreover, we introduce low-rank adaptation by injecting a small trainable GNN alongside the pre-trained one, effectively bridging structural distribution gaps while mitigating the catastrophic forgetting. Additionally, a structure-aware regularization objective is proposed to enhance the adaptability of the pre-trained GNN to target graph with scarce supervision labels. Extensive experiments on eight real-world datasets demonstrate the effectiveness of GraphLoRA against fourteen baselines by tuning only 20% of parameters, even across disparate graph domains. The code is available at https://github.com/AllminerLab/GraphLoRA.