PIMPC-GNN: Physics-Informed Multi-Phase Consensus Learning for Enhancing Imbalanced Node Classification in Graph Neural Networks

2026-02-02

AI Summary

This work addresses the challenge of poor classification performance on minority-class nodes and prediction bias toward majority classes in graph neural networks under class-imbalanced scenarios. The authors propose a multi-phase consensus learning framework that integrates thermodynamic diffusion, Kuramoto synchronization, and spectral embedding, introducing for the first time a physics-inspired multi-phase dynamic mechanism into graph representation learning to enable interpretable consensus modeling. By jointly optimizing a class-adaptive ensemble weighting strategy with an imbalance-aware loss function, the method substantially enhances minority-class recognition. Evaluated on five benchmark datasets, the approach outperforms 16 state-of-the-art methods, achieving up to a 12.7% improvement in minority-class recall and an 8.3% gain in balanced accuracy.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

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}.

Problem

• imbalanced node classification
• graph neural networks
• class imbalance
• minority class
• node classification

Innovation

• Physics-Informed Learning
• Imbalanced Node Classification
• Thermodynamic Diffusion
• Kuramoto Synchronization
• Spectral Embedding