用物理模型提升图神经网络在数据不均衡时的分类效果
PIMPC-GNN: Physics-Informed Multi-Phase Consensus Learning for Enhancing Imbalanced Node Classification in Graph Neural Networks
- 引入热扩散、相位同步和谱嵌入三种物理机制协同优化
- 在五大数据集上少数类召回率最高提升12.7%，平衡准确率提升8.3%
- 适合处理节点分类中类别严重不均衡的问题
图神经网络在类别不均衡场景下表现不佳，少数类样本不足导致预测偏向多数类。本文提出PIMPC-GNN，一种融合物理机制的多阶段共识学习框架。方法结合三种互补动态：(i) 热扩散，用于传播少数类标签以捕捉长程依赖；(ii) Kuramoto同步，通过振荡共识对齐少数类节点；(iii) 谱嵌入，利用结构正则化分离类别。三者通过类别自适应集成加权，并以兼顾平衡交叉熵与物理约束的不平衡感知损失进行训练。在五个基准数据集及5-100的不均衡比例下，该方法超越16种先进基线，少数类召回率最高提升12.7%，平衡准确率最高提升8.3%。框架还提供了图学习中共识动态的可解释性洞察。代码已开源。
原文摘要 · Abstract (English)
Graph neural networks (GNNs) often struggle in class-imbalanced settings, where minority classes are under-represented and predictions are biased toward majorities. We propose \textbf{PIMPC-GNN}, a physics-informed multi-phase consensus framework for imbalanced node classification. Our method integrates three complementary dynamics: (i) thermodynamic diffusion, which spreads minority labels to capture long-range dependencies, (ii) Kuramoto synchronisation, which aligns minority nodes through oscillatory consensus, and (iii) spectral embedding, which separates classes via structural regularisation. These perspectives are combined through class-adaptive ensemble weighting and trained with an imbalance-aware loss that couples balanced cross-entropy with physics-based constraints. Across five benchmark datasets and imbalance ratios from 5-100, PIMPC-GNN outperforms 16 state-of-the-art baselines, achieving notable gains in minority-class recall (up to +12.7\%) and balanced accuracy (up to +8.3\%). Beyond empirical improvements, the framework also provides interpretable insights into consensus dynamics in graph learning. The code is available at \texttt{https://github.com/afofanah/PIMPC-GNN}.
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。