PLGC: Pseudo-Labeled Graph Condensation

• URL: http://arxiv.org/abs/2601.10358v1
• Date: Thu, 15 Jan 2026 13:02:31 GMT
• Title: PLGC: Pseudo-Labeled Graph Condensation
• Abstract summary: Large graph datasets make training graph neural networks (GNNs) computationally costly.<n>Existing approaches rely on clean, supervised labels, which limits their reliability when labels are scarce, noisy, or inconsistent.<n>We propose Pseudo-Labeled Graph Condensation (PLGC), a self-supervised framework that constructs latent pseudo-labels from node embeddings.
• Score: 11.1647744418267
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large graph datasets make training graph neural networks (GNNs) computationally costly. Graph condensation methods address this by generating small synthetic graphs that approximate the original data. However, existing approaches rely on clean, supervised labels, which limits their reliability when labels are scarce, noisy, or inconsistent. We propose Pseudo-Labeled Graph Condensation (PLGC), a self-supervised framework that constructs latent pseudo-labels from node embeddings and optimizes condensed graphs to match the original graph's structural and feature statistics -- without requiring ground-truth labels. PLGC offers three key contributions: (1) A diagnosis of why supervised condensation fails under label noise and distribution shift. (2) A label-free condensation method that jointly learns latent prototypes and node assignments. (3) Theoretical guarantees showing that pseudo-labels preserve latent structural statistics of the original graph and ensure accurate embedding alignment. Empirically, across node classification and link prediction tasks, PLGC achieves competitive performance with state-of-the-art supervised condensation methods on clean datasets and exhibits substantial robustness under label noise, often outperforming all baselines by a significant margin. Our findings highlight the practical and theoretical advantages of self-supervised graph condensation in noisy or weakly-labeled environments.

Related papers

• DREAM: Dual-Standard Semantic Homogeneity with Dynamic Optimization for Graph Learning with Label Noise [53.55187452152358]
  This paper proposes a novel method, Dual-Standard Semantic Homogeneity with Dynamic Optimization (DREAM) for reliable, relation-informed optimization on graphs with label noise.<n>Specifically, we design a relation-informed dynamic optimization framework that iteratively reevaluates the reliability of each labeled node in the graph.
  arXiv  Detail & Related papers  (2026-01-24T12:54:18Z)
• 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)
• Graph Neural Networks with Coarse- and Fine-Grained Division for Mitigating Label Sparsity and Noise [5.943641527857957]
  Graph Neural Networks (GNNs) have gained prominence in semi-supervised learning tasks in processing graph-structured data. In real-world scenarios, labels on nodes of graphs are inevitably noisy and sparsely labeled, significantly degrading the performance of GNNs. We propose a novel GNN-CFGD that reduces the negative impact of noisy labels via coarse- and fine-grained division, along with graph reconstruction.
  arXiv  Detail & Related papers  (2024-11-06T08:21:26Z)
• 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)
• Simple Graph Condensation [30.85754566420301]
  Graph condensation involves tuning Graph Neural Networks (GNNs) on a small condensed graph for use on a large-scale original graph. We introduce the Simple Graph Condensation (SimGC) framework, which aligns the condensed graph with the original graph from the input layer to the prediction layer. SimGC achieves a significant speedup of up to 10 times compared to existing graph condensation methods.
  arXiv  Detail & Related papers  (2024-03-22T05:04:48Z)
• Resurrecting Label Propagation for Graphs with Heterophily and Label Noise [40.11022005996222]
  Label noise is a common challenge in large datasets, as it can significantly degrade the generalization ability of deep neural networks. We study graph label noise in the context of arbitrary heterophily, with the aim of rectifying noisy labels and assigning labels to previously unlabeled nodes. $R2LP$ is an iterative algorithm with three steps: (1) reconstruct the graph to recover the homophily property, (2) utilize label propagation to rectify the noisy labels, and (3) select high-confidence labels to retain for the next iteration.
  arXiv  Detail & Related papers  (2023-10-25T11:28:26Z)
• Local Graph Clustering with Noisy Labels [8.142265733890918]
  We propose a study of local graph clustering using noisy node labels as a proxy for additional node information. In this setting, nodes receive initial binary labels based on cluster affiliation: 1 if they belong to the target cluster and 0 otherwise. We show that reliable node labels can be obtained with just a few samples from an attributed graph.
  arXiv  Detail & Related papers  (2023-10-12T04:37:15Z)
• 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)
• Unified Robust Training for Graph NeuralNetworks against Label Noise [12.014301020294154]
  We propose a new framework, UnionNET, for learning with noisy labels on graphs under a semi-supervised setting. Our approach provides a unified solution for robustly training GNNs and performing label correction simultaneously.
  arXiv  Detail & Related papers  (2021-03-05T01:17:04Z)
• On the Equivalence of Decoupled Graph Convolution Network and Label Propagation [60.34028546202372]
  Some work shows that coupling is inferior to decoupling, which supports deep graph propagation better. Despite effectiveness, the working mechanisms of the decoupled GCN are not well understood. We propose a new label propagation method named propagation then training Adaptively (PTA), which overcomes the flaws of the decoupled GCN.
  arXiv  Detail & Related papers  (2020-10-23T13:57:39Z)
• Contrastive and Generative Graph Convolutional Networks for Graph-based Semi-Supervised Learning [64.98816284854067]
  Graph-based Semi-Supervised Learning (SSL) aims to transfer the labels of a handful of labeled data to the remaining massive unlabeled data via a graph. A novel GCN-based SSL algorithm is presented in this paper to enrich the supervision signals by utilizing both data similarities and graph structure.
  arXiv  Detail & Related papers  (2020-09-15T13:59:28Z)
• Graph Inference Learning for Semi-supervised Classification [50.55765399527556]
  We propose a Graph Inference Learning framework to boost the performance of semi-supervised node classification. For learning the inference process, we introduce meta-optimization on structure relations from training nodes to validation nodes. Comprehensive evaluations on four benchmark datasets demonstrate the superiority of our proposed GIL when compared against state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-01-17T02:52:30Z)

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.