Robust Graph Condensation via Classification Complexity Mitigation

• URL: http://arxiv.org/abs/2510.26451v1
• Date: Thu, 30 Oct 2025 12:55:21 GMT
• Title: Robust Graph Condensation via Classification Complexity Mitigation
• Authors: Jiayi Luo, Qingyun Sun, Beining Yang, Haonan Yuan, Xingcheng Fu, Yanbiao Ma, Jianxin Li, Philip S. Yu,
• Abstract summary: Graph condensation is an intrinsic-dimension-reducing process, synthesizing a condensed graph with lower classification complexity.<n>We introduce three graph data manifold learning modules that guide the condensed graph to lie within a smooth, low-dimensional manifold.<n>Experiments demonstrate the robustness of ModelName across diverse attack scenarios.
• Score: 61.22258715077984
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Graph condensation (GC) has gained significant attention for its ability to synthesize smaller yet informative graphs. However, existing studies often overlook the robustness of GC in scenarios where the original graph is corrupted. In such cases, we observe that the performance of GC deteriorates significantly, while existing robust graph learning technologies offer only limited effectiveness. Through both empirical investigation and theoretical analysis, we reveal that GC is inherently an intrinsic-dimension-reducing process, synthesizing a condensed graph with lower classification complexity. Although this property is critical for effective GC performance, it remains highly vulnerable to adversarial perturbations. To tackle this vulnerability and improve GC robustness, we adopt the geometry perspective of graph data manifold and propose a novel Manifold-constrained Robust Graph Condensation framework named MRGC. Specifically, we introduce three graph data manifold learning modules that guide the condensed graph to lie within a smooth, low-dimensional manifold with minimal class ambiguity, thereby preserving the classification complexity reduction capability of GC and ensuring robust performance under universal adversarial attacks. Extensive experiments demonstrate the robustness of \ModelName\ across diverse attack scenarios.

Related papers

• Less is More: Towards Simple Graph Contrastive Learning [28.21633108265473]
  Graph Contrastive Learning (GCL) has shown strong promise for unsupervised graph representation learning, yet its effectiveness on heterophilic graphs remains limited.<n>Most existing methods rely on complex augmentation schemes, intricate encoders, or negative sampling.<n>We uncover a simple yet effective principle for GCL: mitigating node feature noise by aggregating it with structural features from the graph topology.
  arXiv  Detail & Related papers  (2025-09-30T03:56:50Z)
• 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)
• Contrastive Graph Condensation: Advancing Data Versatility through Self-Supervised Learning [38.72627860431171]
  Graph condensation is a promising solution to synthesize a compact, substitute graph of the large-scale original graph.<n>We introduce Contrastive Graph Condensation (CTGC), which adopts a self-supervised surrogate task to extract critical, causal information from the original graph.<n>CTGC excels in handling various downstream tasks with a limited number of labels, consistently outperforming state-of-the-art GC methods.
  arXiv  Detail & Related papers  (2024-11-26T03:01:22Z)
• When Witnesses Defend: A Witness Graph Topological Layer for Adversarial Graph Learning [19.566775406771757]
  We bridge adversarial graph learning with the emerging tools from computational topology, namely, persistent homology representations of graphs.<n>We introduce the concept of witness complex to adversarial analysis on graphs, which allows us to focus only on the salient shape characteristics of graphs.<n>Our experiments across six datasets demonstrate that Witness Graph Topological Layer boosts the robustness of GNNs across a range of perturbations and against a range of adversarial attacks.
  arXiv  Detail & Related papers  (2024-09-21T14:53:32Z)
• GC-Bench: An Open and Unified Benchmark for Graph Condensation [54.70801435138878]
  We develop a comprehensive Graph Condensation Benchmark (GC-Bench) to analyze the performance of graph condensation. GC-Bench systematically investigates the characteristics of graph condensation in terms of the following dimensions: effectiveness, transferability, and complexity. We have developed an easy-to-use library for training and evaluating different GC methods to facilitate reproducible research.
  arXiv  Detail & Related papers  (2024-06-30T07:47:34Z)
• GC4NC: A Benchmark Framework for Graph Condensation on Node Classification with New Insights [30.796414860754837]
  Graph condensation (GC) is an emerging technique designed to learn a significantly smaller graph that retains the essential information of the original graph. This paper introduces textbfGC4NC, a comprehensive framework for evaluating diverse GC methods on node classification. Our systematic evaluation offers novel insights into how condensed graphs behave and the critical design choices that drive their success.
  arXiv  Detail & Related papers  (2024-06-24T15:17:49Z)
• RobGC: Towards Robust Graph Condensation [61.259453496191696]
  Graph neural networks (GNNs) have attracted widespread attention for their impressive capability of graph representation learning.<n>However, the increasing prevalence of large-scale graphs presents a significant challenge for GNN training due to their computational demands.<n>We propose graph condensation (GC) to generate an informative compact graph that enables efficient training of GNNs while retaining performance.
  arXiv  Detail & Related papers  (2024-06-19T04:14:57Z)
• Rethinking and Accelerating Graph Condensation: A Training-Free Approach with Class Partition [49.41718583061147]
  Graph condensation is a data-centric solution to replace the large graph with a small yet informative condensed graph.<n>Existing GC methods suffer from intricate optimization processes, necessitating excessive computing resources and training time.<n>We propose a training-free GC framework termed Class-partitioned Graph Condensation (CGC)<n>CGC condenses the Ogbn-products graph within 30 seconds, achieving a speedup ranging from $102$X to $104$X and increasing accuracy by up to 4.2%.
  arXiv  Detail & Related papers  (2024-05-22T14:57:09Z)
• Structure-free Graph Condensation: From Large-scale Graphs to Condensed Graph-free Data [91.27527985415007]
  Existing graph condensation methods rely on the joint optimization of nodes and structures in the condensed graph. We advocate a new Structure-Free Graph Condensation paradigm, named SFGC, to distill a large-scale graph into a small-scale graph node set.
  arXiv  Detail & Related papers  (2023-06-05T07:53:52Z)
• EGC2: Enhanced Graph Classification with Easy Graph Compression [3.599345724913102]
  We propose EGC$2$, an enhanced graph classification model with easy graph compression. EGC$2$ captures the relationship between features of different nodes by constructing feature graphs and improving aggregate node-level representation. Experiments on seven benchmark datasets demonstrate that the proposed feature read-out and graph compression mechanisms enhance the robustness of various basic models.
  arXiv  Detail & Related papers  (2021-07-16T07:17:29Z)

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.