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

• URL: http://arxiv.org/abs/2602.01920v1
• Date: Mon, 02 Feb 2026 10:21:58 GMT
• Title: PIMPC-GNN: Physics-Informed Multi-Phase Consensus Learning for Enhancing Imbalanced Node Classification in Graph Neural Networks
• Authors: Abdul Joseph Fofanah, Lian Wen, David Chen,
• Abstract summary: PIMPC-GNN is a physics-informed consensus framework for imbalanced node classification.<n>Our method integrates three complementary dynamics: (i) thermodynamic diffusion, (ii) Kuramoto synchronisation, and (iii) spectral embedding.<n>Across five benchmark datasets and imbalance ratios from 5-100, PIMPC-GNN outperforms 16 state-of-the-art baselines.
• Score: 4.516559054098262
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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}.

Related papers

• GraphSB: Boosting Imbalanced Node Classification on Graphs through Structural Balance [2.367568291148072]
  Imbalanced node classification is a critical challenge in graph learning, where most existing methods typically utilize Graph Neural Networks (GNNs) to learn node representations.<n>We propose GraphSB, a novel framework that incorporates Structural Balance as a key strategy to address the underlying imbalanced graph structure before node synthesis.
  arXiv  Detail & Related papers  (2025-11-13T06:58:45Z)
• GraphIFE: Rethinking Graph Imbalance Node Classification via Invariant Learning [49.47096910857841]
  Most graph neural networks implicitly assume a balanced class distribution, which can lead to biased learning and degraded performance on minority classes.<n>We propose GraphIFE, a novel framework designed to mitigate quality inconsistency in synthesized nodes.<n>Our approach incorporates two key concepts from graph invariant learning and introduces strategies to strengthen the embedding space representation.
  arXiv  Detail & Related papers  (2025-09-28T03:41:16Z)
• Quantum-Informed Contrastive Learning with Dynamic Mixup Augmentation for Class-Imbalanced Expert Systems [0.0]
  QCL-MixNet is a novel framework for dynamic mixup for robust classification under imbalance.<n>We show that QCL-MixNet consistently outperforms 20 state-of-the-art machine learning, deep learning, and GNN-based baselines in macro-F1 and recall.
  arXiv  Detail & Related papers  (2025-06-16T20:44:30Z)
• Learning to Reweight for Graph Neural Network [63.978102332612906]
  Graph Neural Networks (GNNs) show promising results for graph tasks. Existing GNNs' generalization ability will degrade when there exist distribution shifts between testing and training graph data. We propose a novel nonlinear graph decorrelation method, which can substantially improve the out-of-distribution generalization ability.
  arXiv  Detail & Related papers  (2023-12-19T12:25:10Z)
• Rethinking Semi-Supervised Imbalanced Node Classification from Bias-Variance Decomposition [17.742433178056903]
  This paper introduces a new approach to address the issue of class imbalance in graph neural networks (GNNs) for learning on graph-structured data.<n>Our approach integrates imbalanced node classification and Bias-Variance Decomposition, establishing a theoretical framework that closely relates data imbalance to model variance.
  arXiv  Detail & Related papers  (2023-10-28T17:28:07Z)
• Heterophily-Based Graph Neural Network for Imbalanced Classification [19.51668009720269]
  We introduce a unique approach that tackles imbalanced classification on graphs by considering graph heterophily. We propose Fast Im-GBK, which integrates an imbalance classification strategy with heterophily-aware GNNs. Our experiments on real-world graphs demonstrate our model's superiority in classification performance and efficiency for node classification tasks.
  arXiv  Detail & Related papers  (2023-10-12T21:19:47Z)
• Label Deconvolution for Node Representation Learning on Large-scale Attributed Graphs against Learning Bias [72.33336385797944]
  We propose an efficient label regularization technique, namely Label Deconvolution (LD), to alleviate the learning bias.<n>We show that LD significantly outperforms state-of-the-art methods on Open Graph Benchmark datasets.
  arXiv  Detail & Related papers  (2023-09-26T13:09:43Z)
• Class-Imbalanced Graph Learning without Class Rebalancing [62.1368829847041]
  Class imbalance is prevalent in real-world node classification tasks and poses great challenges for graph learning models. In this work, we approach the root cause of class-imbalance bias from an topological paradigm. We devise a lightweight topological augmentation framework BAT to mitigate the class-imbalance bias without class rebalancing.
  arXiv  Detail & Related papers  (2023-08-27T19:01:29Z)
• A Neural Collapse Perspective on Feature Evolution in Graph Neural Networks [44.31777384413466]
  Graph neural networks (GNNs) have become increasingly popular for classification tasks on graph-structured data. In this paper, we focus on node-wise classification and explore the feature evolution through the lens of the "Neural Collapse" phenomenon. We show that even an "optimistic" mathematical model requires that the graphs obey a strict structural condition in order to possess a minimizer with exact collapse.
  arXiv  Detail & Related papers  (2023-07-04T23:03:21Z)
• Semantic-aware Node Synthesis for Imbalanced Heterogeneous Information Networks [51.55932524129814]
  We present the first method for the semantic imbalance problem in imbalanced HINs named Semantic-aware Node Synthesis (SNS) SNS adaptively selects the heterogeneous neighbor nodes and augments the network with synthetic nodes while preserving the minority semantics. We also introduce two regularization approaches for HGNNs that constrain the representation of synthetic nodes from both semantic and class perspectives.
  arXiv  Detail & Related papers  (2023-02-27T00:21:43Z)
• Position-aware Structure Learning for Graph Topology-imbalance by Relieving Under-reaching and Over-squashing [67.83086131278904]
  Topology-imbalance is a graph-specific imbalance problem caused by the uneven topology positions of labeled nodes. We propose a novel position-aware graph structure learning framework named PASTEL. Our key insight is to enhance the connectivity of nodes within the same class for more supervision information.
  arXiv  Detail & Related papers  (2022-08-17T14:04:21Z)
• Distance-wise Prototypical Graph Neural Network in Node Imbalance Classification [9.755229198654922]
  We propose a novel Distance-wise Prototypical Graph Neural Network (DPGNN) for imbalanced graph data. The proposed DPGNN almost always significantly outperforms all other baselines, which demonstrates its effectiveness in imbalanced node classification.
  arXiv  Detail & Related papers  (2021-10-22T19:43:15Z)
• Graph Classification by Mixture of Diverse Experts [67.33716357951235]
  We present GraphDIVE, a framework leveraging mixture of diverse experts for imbalanced graph classification. With a divide-and-conquer principle, GraphDIVE employs a gating network to partition an imbalanced graph dataset into several subsets. Experiments on real-world imbalanced graph datasets demonstrate the effectiveness of GraphDIVE.
  arXiv  Detail & Related papers  (2021-03-29T14:03:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.