SamGoG: A Sampling-Based Graph-of-Graphs Framework for Imbalanced Graph Classification

• URL: http://arxiv.org/abs/2507.13741v1
• Date: Fri, 18 Jul 2025 08:41:58 GMT
• Title: SamGoG: A Sampling-Based Graph-of-Graphs Framework for Imbalanced Graph Classification
• Authors: Shangyou Wang, Zezhong Ding, Xike Xie,
• Abstract summary: SamGoG is a sampling-based Graph-of-Graphs (GoG) learning framework that effectively mitigates both class and graph size imbalance.<n>Experiments on benchmark datasets demonstrate that SamGoG achieves state-of-the-art performance with up to a 15.66% accuracy improvement.
• Score: 5.644913477933405
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Attribute-Enhanced Similarity Ranking for Sparse Link Prediction [6.774952925054741]
  Graph Neural Networks (GNNs) have become the predominant framework for link prediction.<n>We show that the reported performance of GNNs for link prediction in the balanced setting does not translate to the more realistic imbalanced setting.<n>Experiments show that Gelato, a similarity-based link-prediction method, outperforms existing GNN-based alternatives.
  arXiv  Detail & Related papers  (2024-11-29T21:22:35Z)
• Scale Invariance of Graph Neural Networks [4.002604752467421]
  We address two fundamental challenges in Graph Neural Networks (GNNs)<n>We propose ScaleNet, a unified network architecture that achieves state-of-the-art performance across four homophilic and two heterophilic benchmark datasets.<n>For another popular GNN approach to digraphs, we demonstrate the equivalence between Hermitian Laplacian methods and GraphSAGE with incidence normalization.
  arXiv  Detail & Related papers  (2024-11-28T22:06:06Z)
• GSINA: Improving Subgraph Extraction for Graph Invariant Learning via Graph Sinkhorn Attention [52.67633391931959]
  Graph invariant learning (GIL) has been an effective approach to discovering the invariant relationships between graph data and its labels. We propose a novel graph attention mechanism called Graph Sinkhorn Attention (GSINA) GSINA is able to obtain meaningful, differentiable invariant subgraphs with controllable sparsity and softness.
  arXiv  Detail & Related papers  (2024-02-11T12:57:16Z)
• 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)
• T-GAE: Transferable Graph Autoencoder for Network Alignment [79.89704126746204]
  T-GAE is a graph autoencoder framework that leverages transferability and stability of GNNs to achieve efficient network alignment without retraining. Our experiments demonstrate that T-GAE outperforms the state-of-the-art optimization method and the best GNN approach by up to 38.7% and 50.8%, respectively.
  arXiv  Detail & Related papers  (2023-10-05T02:58:29Z)
• Similarity-aware Positive Instance Sampling for Graph Contrastive Pre-training [82.68805025636165]
  We propose to select positive graph instances directly from existing graphs in the training set. Our selection is based on certain domain-specific pair-wise similarity measurements. Besides, we develop an adaptive node-level pre-training method to dynamically mask nodes to distribute them evenly in the graph.
  arXiv  Detail & Related papers  (2022-06-23T20:12:51Z)
• Training Free Graph Neural Networks for Graph Matching [103.45755859119035]
  TFGM is a framework to boost the performance of Graph Neural Networks (GNNs) based graph matching without training. Applying TFGM on various GNNs shows promising improvements over baselines.
  arXiv  Detail & Related papers  (2022-01-14T09:04:46Z)
• Imbalanced Graph Classification via Graph-of-Graph Neural Networks [16.589373163769853]
  Graph Neural Networks (GNNs) have achieved unprecedented success in learning graph representations to identify categorical labels of graphs. We introduce a novel framework, Graph-of-Graph Neural Networks (G$2$GNN), which alleviates the graph imbalance issue by deriving extra supervision globally from neighboring graphs and locally from graphs themselves. Our proposed G$2$GNN outperforms numerous baselines by roughly 5% in both F1-macro and F1-micro scores.
  arXiv  Detail & Related papers  (2021-12-01T02:25:47Z)
• Is Homophily a Necessity for Graph Neural Networks? [50.959340355849896]
  Graph neural networks (GNNs) have shown great prowess in learning representations suitable for numerous graph-based machine learning tasks. GNNs are widely believed to work well due to the homophily assumption ("like attracts like"), and fail to generalize to heterophilous graphs where dissimilar nodes connect. Recent works design new architectures to overcome such heterophily-related limitations, citing poor baseline performance and new architecture improvements on a few heterophilous graph benchmark datasets as evidence for this notion. In our experiments, we empirically find that standard graph convolutional networks (GCNs) can actually achieve better performance than
  arXiv  Detail & Related papers  (2021-06-11T02:44:00Z)
• Meta-path Free Semi-supervised Learning for Heterogeneous Networks [16.641434334366227]
  Graph neural networks (GNNs) have been widely used in representation learning on graphs and achieved superior performance in tasks such as node classification. In this paper, we propose simple and effective graph neural networks for heterogeneous graph, excluding the use of meta-paths.
  arXiv  Detail & Related papers  (2020-10-18T06:01:58Z)

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.