Remedying Coarsening-Based GNN Training under Heterophily via Adaptive Complementary Enhancement

• URL: http://arxiv.org/abs/2607.21885v1
• Date: Fri, 24 Jul 2026 01:29:28 GMT
• Title: Remedying Coarsening-Based GNN Training under Heterophily via Adaptive Complementary Enhancement
• Abstract summary: We show that existing coarsening-based training methods suffer significant performance degradation on heterophilic graphs due to inevitable loss of graph information during coarsening.<n>We propose bf Adaptive bf Complementary bf Enhancement, a plug-and-play, model-agnostic strategy that reintegrates the information discarded in coarsening.
• Score: 26.45110502081819
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Coarsening-based training for graph neural networks (GNNs), i.e.\ training on coarsened graphs rather than the original large ones, has become a promising direction for scaling GNNs to massive graphs. However, prior work has been evaluated almost exclusively on \textit{homophilic} graphs, leaving the more challenging \textit{heterophilic} settings underexplored. We show, both empirically and theoretically, that existing coarsening-based training methods suffer significant performance degradation on heterophilic graphs due to inevitable loss of graph information during coarsening. To address this, we propose {\bf A}daptive {\bf C}omplementary {\bf E}nhancement, a plug-and-play, model-agnostic strategy that reintegrates the information discarded in coarsening: ACE learns a projector for re-constructing original node features and applies \textit{anisotropic structural regularization} to embed local heterophily. We further adopt \textit{homoscedastic uncertainty weighting} to adaptively balance the combined training objective of primary coarsened-graph training loss and full-graph auxiliary loss with augmented node features re-constructed by the heterophily-aware projector. Extensive experiments show that ACE drives consistent gains on heterophilic benchmarks while preserving competitive results on homophilic graphs with minimal computational overhead. Code is available at the GitHub repository: https://github.com/vasile-paskardlgm/ACE.

Related papers

• Beyond Homophily: Towards Generalized Graph Reconstruction Attack and Defense [80.28330585803133]
  Graph neural networks (GNNs) are widely deployed on computation data, yet they can leak sensitive or proprietary information about the training graph adjacency.<n>This work studies graph reconstruction attacks (GRA), a form of model inversion that reconstructs the training adjacency from a trained GNN.<n>We propose MC-GRA (+), which reconstructs the adjacency by optimizing a surrogate adjacency whose GNN-induced representations align with those of the target model.<n>On the defense side, we propose MC-GPB (+), which suppresses adjacency-dependent information throughout the representation chain
  arXiv  Detail & Related papers  (2026-06-06T09:29:27Z)
• Topology-Aware Gaussian Graph Repair for Robust Graph Neural Networks [1.652121135969053]
  Topology-Aware Gaussian Repair (TAGR) is a simple graph repair framework for robust message passing in graph neural networks.<n>We show that TAGR improves the robustness of graph neural networks under both noisy-edge and missing-edge settings.
  arXiv  Detail & Related papers  (2026-06-02T10:39:24Z)
• Position: Graph Condensation Needs a Reset -- Move Beyond Full-dataset Training and Model-Dependence [26.234880574328823]
  We argue that graph condensation, in its current form, needs a reset.<n>We call for moving beyond full-dataset training and model-dependent design.<n>We aim to reorient the field toward approaches that deliver on the true promise of condensation.
  arXiv  Detail & Related papers  (2026-05-17T07:08:22Z)
• Graph Structure Refinement with Energy-based Contrastive Learning [56.957793274727514]
  We introduce an unsupervised method based on a joint of generative training and discriminative training to learn graph structure and representation.<n>We propose an Energy-based Contrastive Learning (ECL) guided Graph Structure Refinement (GSR) framework, denoted as ECL-GSR.<n>ECL-GSR achieves faster training with fewer samples and memories against the leading baseline, highlighting its simplicity and efficiency in downstream tasks.
  arXiv  Detail & Related papers  (2024-12-20T04:05:09Z)
• Gradient Rewiring for Editable Graph Neural Network Training [84.77778876113099]
  underlineGradient underlineRewiring method for underlineEditable graph neural network training, named textbfGRE. We propose a simple yet effective underlineGradient underlineRewiring method for underlineEditable graph neural network training, named textbfGRE.
  arXiv  Detail & Related papers  (2024-10-21T01:01:50Z)
• Preserving Node Distinctness in Graph Autoencoders via Similarity Distillation [9.395697548237333]
  Graph autoencoders (GAEs) rely on distance-based criteria, such as mean-square-error (MSE) to reconstruct the input graph. relying solely on a single reconstruction criterion may lead to a loss of distinctiveness in the reconstructed graph. We have developed a simple yet effective strategy to preserve the necessary distinctness in the reconstructed graph.
  arXiv  Detail & Related papers  (2024-06-25T12:54:35Z)
• Design Your Own Universe: A Physics-Informed Agnostic Method for Enhancing Graph Neural Networks [34.16727363891593]
  We propose a model-agnostic enhancement framework for Graph Neural Networks (GNNs) This framework enriches the graph structure by introducing additional nodes and rewiring connections with both positive and negative weights. We theoretically verify that GNNs enhanced through our approach can effectively circumvent the over-smoothing issue and exhibit robustness against over-squashing. Empirical validations on benchmarks for homophilic, heterophilic graphs, and long-term graph datasets show that GNNs enhanced by our method significantly outperform their original counterparts.
  arXiv  Detail & Related papers  (2024-01-26T00:47:43Z)
• 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)
• A GAN Approach for Node Embedding in Heterogeneous Graphs Using Subgraph Sampling [33.50085646298074]
  We propose a novel framework that combines Graph Neural Network (GNN) and Generative Adrial Network (GAN) to enhance classification for underrepresented node classes. The framework incorporates an advanced edge generation and selection module, enabling the simultaneous creation of synthetic nodes and edges.
  arXiv  Detail & Related papers  (2023-12-11T16:52:20Z)
• Efficient Heterogeneous Graph Learning via Random Projection [58.4138636866903]
  Heterogeneous Graph Neural Networks (HGNNs) are powerful tools for deep learning on heterogeneous graphs. Recent pre-computation-based HGNNs use one-time message passing to transform a heterogeneous graph into regular-shaped tensors. We propose a hybrid pre-computation-based HGNN, named Random Projection Heterogeneous Graph Neural Network (RpHGNN)
  arXiv  Detail & Related papers  (2023-10-23T01:25:44Z)
• 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)
• Comprehensive Graph Gradual Pruning for Sparse Training in Graph Neural Networks [52.566735716983956]
  We propose a graph gradual pruning framework termed CGP to dynamically prune GNNs. Unlike LTH-based methods, the proposed CGP approach requires no re-training, which significantly reduces the computation costs. Our proposed strategy greatly improves both training and inference efficiency while matching or even exceeding the accuracy of existing methods.
  arXiv  Detail & Related papers  (2022-07-18T14:23:31Z)
• A Graph Data Augmentation Strategy with Entropy Preserving [11.886325179121226]
  We introduce a novel graph entropy definition as a quantitative index to evaluate feature information among a graph. Under considerations of preserving graph entropy, we propose an effective strategy to generate training data using a perturbed mechanism. Our proposed approach significantly enhances the robustness and generalization ability of GCNs during the training process.
  arXiv  Detail & Related papers  (2021-07-13T12:58:32Z)

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.