Adaptive Riemannian Graph Neural Networks

• URL: http://arxiv.org/abs/2508.02600v1
• Date: Mon, 04 Aug 2025 16:55:02 GMT
• Title: Adaptive Riemannian Graph Neural Networks
• Authors: Xudong Wang, Tongxin Li, Chris Ding, Jicong Fan,
• Abstract summary: We introduce a novel framework that learns a continuous and anisotropic metric tensor field over the graph.<n>It allows each node to determine its optimal local geometry, enabling the model to fluidly adapt to the graph's structural landscape.<n>Our method demonstrates superior performance on both homophilic and heterophilic benchmark geometries.
• Score: 29.859977834688625
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Graph data often exhibits complex geometric heterogeneity, where structures with varying local curvature, such as tree-like hierarchies and dense communities, coexist within a single network. Existing geometric GNNs, which embed graphs into single fixed-curvature manifolds or discrete product spaces, struggle to capture this diversity. We introduce Adaptive Riemannian Graph Neural Networks (ARGNN), a novel framework that learns a continuous and anisotropic Riemannian metric tensor field over the graph. It allows each node to determine its optimal local geometry, enabling the model to fluidly adapt to the graph's structural landscape. Our core innovation is an efficient parameterization of the node-wise metric tensor, specializing to a learnable diagonal form that captures directional geometric information while maintaining computational tractability. To ensure geometric regularity and stable training, we integrate a Ricci flow-inspired regularization that smooths the learned manifold. Theoretically, we establish the rigorous geometric evolution convergence guarantee for ARGNN and provide a continuous generalization that unifies prior fixed or mixed-curvature GNNs. Empirically, our method demonstrates superior performance on both homophilic and heterophilic benchmark datasets with the ability to capture diverse structures adaptively. Moreover, the learned geometries both offer interpretable insights into the underlying graph structure and empirically corroborate our theoretical analysis.

Related papers

• Feed-anywhere ANN (I) Steady Discrete $\ o$ Diffusing on Graph Hidden States [0.0]
  We propose a novel framework for learning hidden graph structures from data using geometric analysis and nonlinear dynamics.<n>Our model achieves stronger bounds than standard neural networks, with complexity dependent on the data manifold's topology.
  arXiv  Detail & Related papers  (2025-07-27T00:35:15Z)
• Can we ease the Injectivity Bottleneck on Lorentzian Manifolds for Graph Neural Networks? [0.0]
  Lorentzian Graph Isomorphic Network (LGIN) is a novel HGNN designed for enhanced discrimination within the Lorentzian model.<n>LGIN is the first to adapt principles of powerful, highly discriminative GNN architectures to a Riemannian manifold.
  arXiv  Detail & Related papers  (2025-03-31T18:49:34Z)
• Score-based Pullback Riemannian Geometry: Extracting the Data Manifold Geometry using Anisotropic Flows [10.649159213723106]
  We propose a framework for data-driven Riemannian geometry that is scalable in both geometry and learning.<n>We show that the proposed framework produces high-quality geodesics passing through the data support.<n>This is the first scalable framework for extracting the complete geometry of the data manifold.
  arXiv  Detail & Related papers  (2024-10-02T18:52:12Z)
• Scalable Graph Compressed Convolutions [68.85227170390864]
  We propose a differentiable method that applies permutations to calibrate input graphs for Euclidean convolution. Based on the graph calibration, we propose the Compressed Convolution Network (CoCN) for hierarchical graph representation learning.
  arXiv  Detail & Related papers  (2024-07-26T03:14:13Z)
• A Differential Geometric View and Explainability of GNN on Evolving Graphs [15.228139478280747]
  Graphs are ubiquitous in social networks and biochemistry, where Graph Neural Networks (GNN) are the state-of-the-art models for prediction. We propose a smooth parameterization of the GNN predicted distributions using axiomatic attribution. Experiments on node classification, link prediction, and graph classification tasks with evolving graphs demonstrate the better sparsity, faithfulness, and intuitiveness of the proposed method.
  arXiv  Detail & Related papers  (2024-03-11T04:26:18Z)
• DeepRicci: Self-supervised Graph Structure-Feature Co-Refinement for Alleviating Over-squashing [72.70197960100677]
  Graph Structure Learning (GSL) plays an important role in boosting Graph Neural Networks (GNNs) with a refined graph. GSL solutions usually focus on structure refinement with task-specific supervision (i.e., node classification) or overlook the inherent weakness of GNNs themselves. We propose to study self-supervised graph structure-feature co-refinement for effectively alleviating the issue of over-squashing in typical GNNs.
  arXiv  Detail & Related papers  (2024-01-23T14:06:08Z)
• Improving embedding of graphs with missing data by soft manifolds [51.425411400683565]
  The reliability of graph embeddings depends on how much the geometry of the continuous space matches the graph structure. We introduce a new class of manifold, named soft manifold, that can solve this situation. Using soft manifold for graph embedding, we can provide continuous spaces to pursue any task in data analysis over complex datasets.
  arXiv  Detail & Related papers  (2023-11-29T12:48:33Z)
• Curve Your Attention: Mixed-Curvature Transformers for Graph Representation Learning [77.1421343649344]
  We propose a generalization of Transformers towards operating entirely on the product of constant curvature spaces. We also provide a kernelized approach to non-Euclidean attention, which enables our model to run in time and memory cost linear to the number of nodes and edges.
  arXiv  Detail & Related papers  (2023-09-08T02:44:37Z)
• How Curvature Enhance the Adaptation Power of Framelet GCNs [27.831929635701886]
  Graph neural network (GNN) has been demonstrated powerful in modeling graph-structured data. This paper introduces a new approach to enhance GNN by discrete graph Ricci curvature. We show that our curvature-based GNN model outperforms the state-of-the-art baselines in both homophily and heterophily graph datasets.
  arXiv  Detail & Related papers  (2023-07-19T06:05:33Z)
• Torsion Graph Neural Networks [21.965704710488232]
  We propose TorGNN, an analytic torsion enhanced Graph Neural Network model. In our TorGNN, for each edge, a corresponding local simplicial complex is identified, then the analytic torsion is calculated. It has been found that our TorGNN can achieve superior performance on both tasks, and outperform various state-of-the-art models.
  arXiv  Detail & Related papers  (2023-06-23T15:02:23Z)
• kHGCN: Tree-likeness Modeling via Continuous and Discrete Curvature Learning [39.25873010585029]
  This study endeavors to explore the curvature between discrete structure and continuous learning space, aiming at encoding the message conveyed by the network topology in the learning process. A curvature-aware hyperbolic graph convolutional neural network, kappaHGCN, is proposed, which utilizes the curvature to guide message passing and improve long-range propagation.
  arXiv  Detail & Related papers  (2022-12-04T10:45:42Z)
• ACE-HGNN: Adaptive Curvature Exploration Hyperbolic Graph Neural Network [72.16255675586089]
  We propose an Adaptive Curvature Exploration Hyperbolic Graph NeuralNetwork named ACE-HGNN to adaptively learn the optimal curvature according to the input graph and downstream tasks. Experiments on multiple real-world graph datasets demonstrate a significant and consistent performance improvement in model quality with competitive performance and good generalization ability.
  arXiv  Detail & Related papers  (2021-10-15T07:18:57Z)
• Semi-Riemannian Graph Convolutional Networks [36.09315878397234]
  We develop a principled Semi-Riemannian GCN that first models data in semi-Riemannian manifold of constant nonzero curvature. Our method provides a geometric inductive bias that is sufficiently flexible to model mixed heterogeneous topologies like hierarchical graphs with cycles.
  arXiv  Detail & Related papers  (2021-06-06T14:23:34Z)
• Gauge Equivariant Mesh CNNs: Anisotropic convolutions on geometric graphs [81.12344211998635]
  A common approach to define convolutions on meshes is to interpret them as a graph and apply graph convolutional networks (GCNs) We propose Gauge Equivariant Mesh CNNs which generalize GCNs to apply anisotropic gauge equivariant kernels. Our experiments validate the significantly improved expressivity of the proposed model over conventional GCNs and other methods.
  arXiv  Detail & Related papers  (2020-03-11T17:21:15Z)

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.