Enhancing Graph Classification Robustness with Singular Pooling

• URL: http://arxiv.org/abs/2510.22643v1
• Date: Sun, 26 Oct 2025 12:07:06 GMT
• Title: Enhancing Graph Classification Robustness with Singular Pooling
• Authors: Sofiane Ennadir, Oleg Smirnov, Yassine Abbahaddou, Lele Cao, Johannes F. Lutzeyer,
• Abstract summary: Graph Neural Networks (GNNs) have achieved strong performance across a range of graph representation learning tasks, yet their adversarial robustness in graph classification remains underexplored compared to node classification.<n>We present a theoretical analysis of standard flat pooling methods, deriving upper bounds on their adversarial risk and identifying their vulnerabilities under different attack scenarios and graph structures.<n>Motivated by these insights, we propose textitRobust Singular Pooling (RS-Pool), a novel pooling strategy that leverages the dominant singular vector of the node embedding matrix to construct a robust graph-level representation.
• Score: 11.537806919295098
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Graph Neural Networks (GNNs) have achieved strong performance across a range of graph representation learning tasks, yet their adversarial robustness in graph classification remains underexplored compared to node classification. While most existing defenses focus on the message-passing component, this work investigates the overlooked role of pooling operations in shaping robustness. We present a theoretical analysis of standard flat pooling methods (sum, average and max), deriving upper bounds on their adversarial risk and identifying their vulnerabilities under different attack scenarios and graph structures. Motivated by these insights, we propose \textit{Robust Singular Pooling (RS-Pool)}, a novel pooling strategy that leverages the dominant singular vector of the node embedding matrix to construct a robust graph-level representation. We theoretically investigate the robustness of RS-Pool and interpret the resulting bound leading to improved understanding of our proposed pooling operator. While our analysis centers on Graph Convolutional Networks (GCNs), RS-Pool is model-agnostic and can be implemented efficiently via power iteration. Empirical results on real-world benchmarks show that RS-Pool provides better robustness than the considered pooling methods when subject to state-of-the-art adversarial attacks while maintaining competitive clean accuracy. Our code is publicly available at:\href{https://github.com/king/rs-pool}{https://github.com/king/rs-pool}.

Related papers

• Geometry-Aware Edge Pooling for Graph Neural Networks [23.216349399814643]
  Graph Neural Networks (GNNs) have shown significant success for graph-based tasks.<n>Motivated by the prevalence of large datasets in real-world applications, pooling layers are crucial components of GNNs.<n>We propose novel graph pooling layers for structure-aware pooling via edge collapses.
  arXiv  Detail & Related papers  (2025-06-13T12:01:46Z)
• BN-Pool: a Bayesian Nonparametric Approach to Graph Pooling [6.952045528182883]
  We introduce BN-Pool, the first clustering-based pooling method for Graph Neural Networks (GNNs)<n> BN-Pool adaptively determines the number of supernodes in a coarsened graph.<n>We show that BN-Pool achieves superior performance across diverse benchmarks.
  arXiv  Detail & Related papers  (2025-01-16T20:15:12Z)
• 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)
• Careful Selection and Thoughtful Discarding: Graph Explicit Pooling Utilizing Discarded Nodes [53.08068729187698]
  We introduce a novel Graph Explicit Pooling (GrePool) method, which selects nodes by explicitly leveraging the relationships between the nodes and final representation vectors crucial for classification. We conduct comprehensive experiments across 12 widely used datasets to validate our proposed method's effectiveness.
  arXiv  Detail & Related papers  (2023-11-21T14:44:51Z)
• Edge-aware Hard Clustering Graph Pooling for Brain Imaging [8.425787611090776]
  We propose a novel edge-aware hard clustering graph pool (EHCPool), which is tailored to dominant edge features and redefines the clustering process. EHCPool has the potential to probe different types of dysfunctional brain networks from a data-driven perspective.
  arXiv  Detail & Related papers  (2023-08-23T04:29:40Z)
• A Comprehensive Study on Large-Scale Graph Training: Benchmarking and Rethinking [124.21408098724551]
  Large-scale graph training is a notoriously challenging problem for graph neural networks (GNNs) We present a new ensembling training manner, named EnGCN, to address the existing issues. Our proposed method has achieved new state-of-the-art (SOTA) performance on large-scale datasets.
  arXiv  Detail & Related papers  (2022-10-14T03:43:05Z)
• Higher-order Clustering and Pooling for Graph Neural Networks [77.47617360812023]
  Graph Neural Networks achieve state-of-the-art performance on a plethora of graph classification tasks. HoscPool is a clustering-based graph pooling operator that captures higher-order information hierarchically. We evaluate HoscPool on graph classification tasks and its clustering component on graphs with ground-truth community structure.
  arXiv  Detail & Related papers  (2022-09-02T09:17:10Z)
• Edge but not Least: Cross-View Graph Pooling [76.71497833616024]
  This paper presents a cross-view graph pooling (Co-Pooling) method to better exploit crucial graph structure information. Through cross-view interaction, edge-view pooling and node-view pooling seamlessly reinforce each other to learn more informative graph-level representations.
  arXiv  Detail & Related papers  (2021-09-24T08:01:23Z)
• Structure-Aware Hierarchical Graph Pooling using Information Bottleneck [2.7088996845250897]
  Graph pooling is an essential ingredient of Graph Neural Networks (GNNs) in graph classification and regression tasks. We propose a novel pooling method named as HIBPool where we leverage the Information Bottleneck (IB) principle. We also introduce a novel structure-aware Discriminative Pooling Readout (DiP-Readout) function to capture the informative local subgraph structures in the graph.
  arXiv  Detail & Related papers  (2021-04-27T07:27:43Z)
• Graph Structure Learning for Robust Graph Neural Networks [63.04935468644495]
  Graph Neural Networks (GNNs) are powerful tools in representation learning for graphs. Recent studies show that GNNs are vulnerable to carefully-crafted perturbations, called adversarial attacks. We propose a general framework Pro-GNN, which can jointly learn a structural graph and a robust graph neural network model.
  arXiv  Detail & Related papers  (2020-05-20T17:07:05Z)

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.