ReDiSC: A Reparameterized Masked Diffusion Model for Scalable Node Classification with Structured Predictions

• URL: http://arxiv.org/abs/2507.14484v1
• Date: Sat, 19 Jul 2025 04:46:53 GMT
• Title: ReDiSC: A Reparameterized Masked Diffusion Model for Scalable Node Classification with Structured Predictions
• Authors: Yule Li, Yifeng Lu, Zhen Wang, Zhewei Wei, Yaliang Li, Bolin Ding,
• Abstract summary: We propose ReDiSC, a structured diffusion model for structured node classification.<n>We show that ReDiSC achieves superior or highly competitive performance compared to state-of-the-art GNN, label propagation, and diffusion-based baselines.<n> Notably, ReDiSC scales effectively to large-scale datasets on which previous structured diffusion methods fail due to computational constraints.
• Score: 64.17845687013434
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In recent years, graph neural networks (GNN) have achieved unprecedented successes in node classification tasks. Although GNNs inherently encode specific inductive biases (e.g., acting as low-pass or high-pass filters), most existing methods implicitly assume conditional independence among node labels in their optimization objectives. While this assumption is suitable for traditional classification tasks such as image recognition, it contradicts the intuitive observation that node labels in graphs remain correlated, even after conditioning on the graph structure. To make structured predictions for node labels, we propose ReDiSC, namely, Reparameterized masked Diffusion model for Structured node Classification. ReDiSC estimates the joint distribution of node labels using a reparameterized masked diffusion model, which is learned through the variational expectation-maximization (EM) framework. Our theoretical analysis shows the efficiency advantage of ReDiSC in the E-step compared to DPM-SNC, a state-of-the-art model that relies on a manifold-constrained diffusion model in continuous domain. Meanwhile, we explicitly link ReDiSC's M-step objective to popular GNN and label propagation hybrid approaches. Extensive experiments demonstrate that ReDiSC achieves superior or highly competitive performance compared to state-of-the-art GNN, label propagation, and diffusion-based baselines across both homophilic and heterophilic graphs of varying sizes. Notably, ReDiSC scales effectively to large-scale datasets on which previous structured diffusion methods fail due to computational constraints, highlighting its significant practical advantage in structured node classification tasks.

Related papers

• Sheaf Graph Neural Networks via PAC-Bayes Spectral Optimization [3.2771631221674333]
  Over-smoothing in Graph Neural Networks (GNNs) causes collapse in distinct node features.<n>We introduce a novel scheme called SGPC (Sheaf GNNs with PAC-Bayes)<n>We show that SGPC outperforms state-of-the-art spectral and sheaf-based GNNs while providing certified confidence intervals on unseen nodes.
  arXiv  Detail & Related papers  (2025-08-01T06:39:28Z)
• Chasing Fairness in Graphs: A GNN Architecture Perspective [73.43111851492593]
  We propose textsfFair textsfMessage textsfPassing (FMP) designed within a unified optimization framework for graph neural networks (GNNs) In FMP, the aggregation is first adopted to utilize neighbors' information and then the bias mitigation step explicitly pushes demographic group node presentation centers together. Experiments on node classification tasks demonstrate that the proposed FMP outperforms several baselines in terms of fairness and accuracy on three real-world datasets.
  arXiv  Detail & Related papers  (2023-12-19T18:00:15Z)
• Heterophily-Aware Graph Attention Network [42.640057865981156]
  Graph Neural Networks (GNNs) have shown remarkable success in graph representation learning. Existing heterophilic GNNs tend to ignore the modeling of heterophily of each edge, which is also a vital part in tackling the heterophily problem. We propose a novel Heterophily-Aware Graph Attention Network (HA-GAT) by fully exploring and utilizing the local distribution as the underlying heterophily.
  arXiv  Detail & Related papers  (2023-02-07T03:21:55Z)
• OrthoReg: Improving Graph-regularized MLPs via Orthogonality Regularization [66.30021126251725]
  Graph Neural Networks (GNNs) are currently dominating in modeling graphstructure data. Graph-regularized networks (GR-MLPs) implicitly inject the graph structure information into model weights, while their performance can hardly match that of GNNs in most tasks. We show that GR-MLPs suffer from dimensional collapse, a phenomenon in which the largest a few eigenvalues dominate the embedding space. We propose OrthoReg, a novel GR-MLP model to mitigate the dimensional collapse issue.
  arXiv  Detail & Related papers  (2023-01-31T21:20:48Z)
• Unifying Label-inputted Graph Neural Networks with Deep Equilibrium Models [12.71307159013144]
  This work unifies the two Graph Neural Networks (GNNs) by interpreting LGNN in the theory of Implicit GNN (IGNN) IGNN exploits information in the entire graph to capture long-range dependencies, but with its network constrained to guarantee the existence of the equilibrium. In this work, implicit differentiation of IGNN is introduced to differentiate its infinite-range label propagation constant memory, making the propagation both distant and adaptive.
  arXiv  Detail & Related papers  (2022-11-19T09:28:53Z)
• Revisiting Heterophily For Graph Neural Networks [42.41238892727136]
  Graph Neural Networks (GNNs) extend basic Neural Networks (NNs) by using graph structures based on the relational inductive bias (homophily assumption) Recent work has identified a non-trivial set of datasets where their performance compared to NNs is not satisfactory.
  arXiv  Detail & Related papers  (2022-10-14T08:00:26Z)
• Relation Embedding based Graph Neural Networks for Handling Heterogeneous Graph [58.99478502486377]
  We propose a simple yet efficient framework to make the homogeneous GNNs have adequate ability to handle heterogeneous graphs. Specifically, we propose Relation Embedding based Graph Neural Networks (RE-GNNs), which employ only one parameter per relation to embed the importance of edge type relations and self-loop connections.
  arXiv  Detail & Related papers  (2022-09-23T05:24:18Z)
• Descent Steps of a Relation-Aware Energy Produce Heterogeneous Graph Neural Networks [25.59092732148598]
  Heterogeneous graph neural networks (GNNs) achieve strong performance on node classification tasks in a semi-supervised learning setting. We propose a novel heterogeneous GNN architecture in which layers are derived from optimization steps that descend a novel relation-aware energy function.
  arXiv  Detail & Related papers  (2022-06-22T13:48:08Z)
• ResNorm: Tackling Long-tailed Degree Distribution Issue in Graph Neural Networks via Normalization [80.90206641975375]
  This paper focuses on improving the performance of GNNs via normalization. By studying the long-tailed distribution of node degrees in the graph, we propose a novel normalization method for GNNs. The $scale$ operation of ResNorm reshapes the node-wise standard deviation (NStd) distribution so as to improve the accuracy of tail nodes.
  arXiv  Detail & Related papers  (2022-06-16T13:49:09Z)
• Mixed Graph Contrastive Network for Semi-Supervised Node Classification [63.924129159538076]
  We propose a novel graph contrastive learning method, termed Mixed Graph Contrastive Network (MGCN)<n>In our method, we improve the discriminative capability of the latent embeddings by an unperturbed augmentation strategy and a correlation reduction mechanism.<n>By combining the two settings, we extract rich supervision information from both the abundant nodes and the rare yet valuable labeled nodes for discriminative representation learning.
  arXiv  Detail & Related papers  (2022-06-06T14:26:34Z)
• Neural Structured Prediction for Inductive Node Classification [29.908759584092167]
  This paper studies node classification in the inductive setting, aiming to learn a model on labeled training graphs and generalize it to infer node labels on unlabeled test graphs. We present a new approach called the Structured Proxy Network (SPN), which combines the advantages of both worlds.
  arXiv  Detail & Related papers  (2022-04-15T15:50:27Z)
• Stochastic Aggregation in Graph Neural Networks [9.551282469099887]
  Graph neural networks (GNNs) manifest pathologies including over-smoothing and limited power discriminating. We present a unifying framework for aggregation (STAG) in GNNs, where noise is (adaptively) injected into the aggregation process from the neighborhood to form node embeddings.
  arXiv  Detail & Related papers  (2021-02-25T02:52:03Z)
• Cyclic Label Propagation for Graph Semi-supervised Learning [52.102251202186025]
  We introduce a novel framework for graph semi-supervised learning called CycProp. CycProp integrates GNNs into the process of label propagation in a cyclic and mutually reinforcing manner. In particular, our proposed CycProp updates the node embeddings learned by GNN module with the augmented information by label propagation.
  arXiv  Detail & Related papers  (2020-11-24T02:55:40Z)

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.