通过边界子图混合提升跨域图预训练效率与效果
MDGMIX: Boundary-Aware Subgraph Mixing for Multi-Domain Graph Pre-Training
- 基于边界节点构建混合子图，实现跨域知识融合
- 在少样本分类任务中优于基线模型，且节省时间和内存
- 适合需要高效跨域图学习的研究者与应用
多领域图预训练是构建具备跨域泛化能力的基础图模型的关键步骤。然而，现有方法大多依赖联合训练所有源域图数据，导致计算成本高。此外，尚不清楚所有源域数据是否对迁移具有同等贡献。本文实证发现多领域图预训练存在显著数据冗余。基于此，提出多领域图预训练框架MDGMIX，结合边界感知子图混合与层级判别机制。通过选取边界节点构建具有挑战性的跨域子图，利用粗粒度域判别和细粒度域分解损失，分离共享模式与域特定模式。在适配阶段，采用轻量级提示加权机制迁移源域知识。大量实验表明，MDGMIX在少样本分类任务中持续优于强基线，同时具备更优的时间与内存效率。代码已开源：https://github.com/zhengziyu77/MDGMIX。
原文摘要 · Abstract (English)
Multi-domain graph pre-training is a crucial step in constructing foundational graph models with cross-domain generalization capabilities. However, existing methods predominantly rely on jointly training all source domain graphs, resulting in high computational costs. Furthermore, it remains unclear whether all source domain graph data contribute equally to effective transfer. This paper empirically reveals significant data redundancy in multi-domain graph pre-training. Based on this finding, we propose the Multi-domain Graph Pre-training Framework, MDGMIX, which combines boundary-aware subgraph mixing with hierarchical discrimination. By selecting boundary nodes to construct challenging mixed-domain subgraphs, MDGMIX employs coarse-grained domain discrimination and fine-grained domain decomposition losses to decouple shared patterns from domain-specific patterns. During adaptation, MDGMIX employs a lightweight prompt weighting mechanism to transfer source domain knowledge. Extensive experiments demonstrate that MDGMIX consistently outperforms strong baselines in few-shot classification tasks while exhibiting superior time and memory efficiency. The code is available at: https://github.com/zhengziyu77/MDGMIX.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。