arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2409.16670cs.LGcs.AI
收藏

GraphLoRA:用于跨图迁移学习的结构感知对比低秩自适应

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

Sun Yat-sen University(中山大学);HKUST(GZ)(香港科技大学(广州));HKUST(香港科技大学)

Zhe-Rui Yang, Jindong Han, Chang-Dong Wang, Hao Liu

AI总结:

本文提出GraphLoRA,通过SMMD分布对齐、低秩可训练GNN和结构感知正则化,实现参数高效的跨图GNN迁移,并在八个数据集上优于十四个基线。

摘要:

图神经网络(GNN)在处理电子商务和社交网络等多个领域的一系列图分析任务方面表现出了卓越能力。尽管GNN具有多功能性,但它们在可迁移性方面面临重大挑战,限制了其在现实应用中的效用。现有的GNN迁移学习研究忽视了不同图数据集之间的分布差异,在跨不同分布迁移时面临挑战。如何有效地将训练良好的GNN应用于具有不同特征和结构分布的新图,仍是一个尚未充分探索的问题。受低秩自适应(LoRA)在使大型语言模型适应各种领域方面取得成功的启发,我们提出GraphLoRA,这是一种有效且参数高效的方法,用于将训练良好的GNN迁移到多样化的图领域。具体而言,我们首先提出结构感知最大均值差异(SMMD),以对齐源图和目标图之间不同的节点特征分布。此外,我们通过在预训练GNN旁注入一个小型可训练GNN来引入低秩自适应,有效弥合结构分布差距,同时缓解灾难性遗忘。此外,提出了一个结构感知正则化目标,以增强预训练GNN对监督标签稀缺的目标图的适应能力。在八个真实世界数据集上的大量实验表明,仅调整20%的参数,GraphLoRA即使在不同图领域之间也优于十四个基线。代码可在https://github.com/AllminerLab/GraphLoRA获取。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑