Mitigating topology biases in Graph Diffusion via Counterfactual Intervention

• URL: http://arxiv.org/abs/2603.02005v1
• Date: Mon, 02 Mar 2026 15:55:07 GMT
• Title: Mitigating topology biases in Graph Diffusion via Counterfactual Intervention
• Authors: Wendi Wang, Jiaxi Yang, Yongkang Du, Lu Lin,
• Abstract summary: Graph diffusion models often inherit and amplify topology biases from sensitive attributes, leading to unfair synthetic graphs.<n>We propose Fair Graph Diffusion Model (FairGDiff), a counterfactual-based one-step solution that mitigates topology biases while balancing fairness and utility.<n>We show that FairGDiff achieves a superior trade-off between fairness and utility, outperforming existing fair graph generation methods.
• Score: 12.080488237241907
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Graph diffusion models have gained significant attention in graph generation tasks, but they often inherit and amplify topology biases from sensitive attributes (e.g. gender, age, region), leading to unfair synthetic graphs. Existing fair graph generation using diffusion models is limited to specific graph-based applications with complete labels or requires simultaneous updates for graph structure and node attributes, making them unsuitable for general usage. To relax these limitations by applying the debiasing method directly on graph topology, we propose Fair Graph Diffusion Model (FairGDiff), a counterfactual-based one-step solution that mitigates topology biases while balancing fairness and utility. In detail, we construct a causal model to capture the relationship between sensitive attributes, biased link formation, and the generated graph structure. By answering the counterfactual question "Would the graph structure change if the sensitive attribute were different?", we estimate an unbiased treatment and incorporate it into the diffusion process. FairGDiff integrates counterfactual learning into both forward diffusion and backward denoising, ensuring that the generated graphs are independent of sensitive attributes while preserving structural integrity. Extensive experiments on real-world datasets demonstrate that FairGDiff achieves a superior trade-off between fairness and utility, outperforming existing fair graph generation methods while maintaining scalability.

Related papers

• Graph Diffusion Counterfactual Explanation [0.8594140167290097]
  We introduce Graph Diffusion Counterfactual Explanation, a novel framework for generating counterfactual explanations on graph data.<n>We empirically demonstrate that our method reliably generates in-distribution as well as minimally structurally different counterfactuals for both discrete classification targets and continuous properties.
  arXiv  Detail & Related papers  (2025-11-20T12:06:53Z)
• Estimating Fair Graphs from Graph-Stationary Data [58.94389691379349]
  We consider group and individual fairness for graphs corresponding to group- and node-level definitions.<n>To evaluate the fairness of a given graph, we provide multiple bias metrics, including novel measurements in the spectral domain.<n>One variant of FairSpecTemp exploits commutativity properties of graph stationarity while directly constraining bias.<n>The other implicitly encourages fair estimates by restricting bias in the graph spectrum and is thus more flexible.
  arXiv  Detail & Related papers  (2025-10-08T20:51:57Z)
• DiffGraph: Heterogeneous Graph Diffusion Model [16.65576765238224]
  Graph Neural Networks (GNNs) have revolutionized graph-structured data modeling, yet traditional GNNs struggle with complex heterogeneous structures prevalent in real-world scenarios.<n>We present the Heterogeneous Graph Diffusion Model (DiffGraph), a pioneering framework that introduces an innovative cross-view denoising strategy.<n>At its core, DiffGraph features a sophisticated latent heterogeneous graph diffusion mechanism, implementing a novel forward and backward diffusion process for superior noise management.
  arXiv  Detail & Related papers  (2025-01-04T15:30:48Z)
• Graph Size-imbalanced Learning with Energy-guided Structural Smoothing [13.636616140250908]
  Real-world graphs usually suffer from the size-imbalanced problem in the multi-graph classification.<n>Recent studies find that off-the-shelf Graph Neural Networks (GNNs) would compromise model performance under the long-tailed settings.<n>We propose a novel energy-based size-imbalanced learning framework named textbfSIMBA, which smooths the features between head and tail graphs.
  arXiv  Detail & Related papers  (2024-12-23T14:06:49Z)
• Motif-Consistent Counterfactuals with Adversarial Refinement for Graph-Level Anomaly Detection [30.618065157205507]
  We propose a novel approach, Motif-consistent Counterfactuals with Adversarial Refinement (MotifCAR) for graph-level anomaly detection. The model combines the motif of one graph, the core subgraph containing the identification (category) information, and the contextual subgraph of another graph to produce a raw counterfactual graph. MotifCAR can generate high-quality counterfactual graphs.
  arXiv  Detail & Related papers  (2024-07-18T08:04:57Z)
• Advancing Graph Generation through Beta Diffusion [49.49740940068255]
  Graph Beta Diffusion (GBD) is a generative model specifically designed to handle the diverse nature of graph data. We propose a modulation technique that enhances the realism of generated graphs by stabilizing critical graph topology.
  arXiv  Detail & Related papers  (2024-06-13T17:42:57Z)
• GraphMaker: Can Diffusion Models Generate Large Attributed Graphs? [7.330479039715941]
  Large-scale graphs with node attributes are increasingly common in various real-world applications. Traditional graph generation methods are limited in their capacity to handle these complex structures. This paper introduces a novel diffusion model, GraphMaker, specifically designed for generating large attributed graphs.
  arXiv  Detail & Related papers  (2023-10-20T22:12:46Z)
• Supercharging Graph Transformers with Advective Diffusion [28.40109111316014]
  This paper proposes Advective Diffusion Transformer (AdvDIFFormer), a physics-inspired graph Transformer model designed to address this challenge.<n>We show that AdvDIFFormer has provable capability for controlling generalization error with topological shifts.<n> Empirically, the model demonstrates superiority in various predictive tasks across information networks, molecular screening and protein interactions.
  arXiv  Detail & Related papers  (2023-10-10T08:40:47Z)
• Graph Generation with Diffusion Mixture [57.78958552860948]
  Generation of graphs is a major challenge for real-world tasks that require understanding the complex nature of their non-Euclidean structures. We propose a generative framework that models the topology of graphs by explicitly learning the final graph structures of the diffusion process.
  arXiv  Detail & Related papers  (2023-02-07T17:07:46Z)
• Beyond spectral gap: The role of the topology in decentralized learning [58.48291921602417]
  In data-parallel optimization of machine learning models, workers collaborate to improve their estimates of the model. This paper aims to paint an accurate picture of sparsely-connected distributed optimization when workers share the same data distribution. Our theory matches empirical observations in deep learning, and accurately describes the relative merits of different graph topologies.
  arXiv  Detail & Related papers  (2022-06-07T08:19:06Z)
• Unbiased Graph Embedding with Biased Graph Observations [52.82841737832561]
  We propose a principled new way for obtaining unbiased representations by learning from an underlying bias-free graph. Based on this new perspective, we propose two complementary methods for uncovering such an underlying graph.
  arXiv  Detail & Related papers  (2021-10-26T18:44:37Z)
• Hyperbolic Graph Embedding with Enhanced Semi-Implicit Variational Inference [48.63194907060615]
  We build off of semi-implicit graph variational auto-encoders to capture higher-order statistics in a low-dimensional graph latent representation. We incorporate hyperbolic geometry in the latent space through a Poincare embedding to efficiently represent graphs exhibiting hierarchical structure.
  arXiv  Detail & Related papers  (2020-10-31T05:48:34Z)

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.