解决图分类中的类别与图大小双重不平衡问题，提升模型性能与训练效率。
SamGoG: A Sampling-Based Graph-of-Graphs Framework for Imbalanced Graph Classification
- 基于重要性采样构建多图图（GoG），动态优化图结构。
- 在多个基准数据集上实现最高15.66%准确率提升，训练加速6.7倍。
- 适用于各类下游GNN模型，适合处理真实世界不平衡图数据。
图神经网络（GNN）在图分类任务中表现出色，能同时捕捉结构与特征信息。然而，真实世界图数据常面临两类关键失衡：类别不平衡和图规模不平衡，导致学习偏差并降低模型性能。现有方法通常仅解决其中一类失衡，或计算成本过高。本文提出SamGoG，一种基于采样的图图（Graph-of-Graphs, GoG）学习框架，有效缓解类别与图大小双重失衡。SamGoG通过高效的基于重要性的采样机制构建多个GoG，并依次进行训练。该机制引入可学习的成对相似性与自适应的GoG节点度，增强边同质性，从而提升下游模型质量。SamGoG可无缝集成多种下游GNN，实现高效适配。大量实验表明，其在基准数据集上达到最先进性能，准确率最高提升15.66%，训练速度加速6.7倍。
原文摘要 · Abstract (English)
Graph Neural Networks (GNNs) have shown remarkable success in graph classification tasks by capturing both structural and feature-based representations. However, real-world graphs often exhibit two critical forms of imbalance: class imbalance and graph size imbalance. These imbalances can bias the learning process and degrade model performance. Existing methods typically address only one type of imbalance or incur high computational costs. In this work, we propose SamGoG, a sampling-based Graph-of-Graphs (GoG) learning framework that effectively mitigates both class and graph size imbalance. SamGoG constructs multiple GoGs through an efficient importance-based sampling mechanism and trains on them sequentially. This sampling mechanism incorporates the learnable pairwise similarity and adaptive GoG node degree to enhance edge homophily, thus improving downstream model quality. SamGoG can seamlessly integrate with various downstream GNNs, enabling their efficient adaptation for graph classification tasks. Extensive experiments on benchmark datasets demonstrate that SamGoG achieves state-of-the-art performance with up to a 15.66% accuracy improvement with 6.7$\times$ training acceleration.
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。