Structure-Centric Graph Foundation Model via Geometric Bases

• URL: http://arxiv.org/abs/2605.08689v1
• Date: Sat, 09 May 2026 04:56:21 GMT
• Title: Structure-Centric Graph Foundation Model via Geometric Bases
• Abstract summary: We propose Structure-Centric Graph Foundation Models (SCGFM) to treat graph topology as the primary source of transferable knowledge.<n>SCGFM introduces learnable geometric bases that define a shared structural coordinate system.<n>Experiments on graph- and node-level tasks demonstrate strong in-domain and cross-domain generalization, outperforming existing GFM approaches.
• Score: 16.191907209297362
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Graph foundation models (GFMs) seek transferable representations across graph domains but are limited by structural heterogeneity and incompatible node feature spaces. We propose Structure-Centric Graph Foundation Models (SCGFM), which treat graph topology as the primary source of transferable knowledge. Modeling graphs as metric measure spaces, SCGFM introduces learnable geometric bases that define a shared structural coordinate system. Graphs are aligned to these bases via Gromov-Wasserstein distances, yielding structure-aligned latent representations that accommodate heterogeneous graph topologies. To address feature incompatibility, SCGFM employs a structure-aware feature re-encoding mechanism that unifies node representations without assuming a fixed feature dimensionality or requiring dataset-specific preprocessing. Experiments on graph- and node-level tasks demonstrate strong in-domain and cross-domain generalization, outperforming existing GFM approaches.

Related papers

• Neural Message Passing on Structural Interaction Graphs for Fully-Inductive Graph Neural Networks [1.49251567571938]
  SIGIL is a framework that maps any attributed graph to a unified representation space of fixed dimension.<n>A relational message-passing network embeds each feature dimension into a shared space.<n>A single SIGIL model, pretrained on one graph, delivers strong fully-inductive link prediction.
  arXiv  Detail & Related papers  (2026-08-09T08:14:35Z)
• Riemannian Geometry Speaks Louder Than Words: From Graph Foundation Model to Next-Generation Graph Intelligence [51.30336200738606]
  There is strong agreement that Graph Foundation Models (GFMs) are essential for advancing graph learning.<n> considerable disagreement persists on how to build a powerful, general-purpose GFM analogous to Large Language Models (LLMs)
  arXiv  Detail & Related papers  (2026-03-23T05:49:19Z)
• Learning the Structure of Connection Graphs [13.687470962704744]
  Connection graphs (CGs) extend traditional graph models by coupling network topology with transformations, enabling the representation of global geometric consistency.<n>We propose a principled framework based on maximum pseudo-likelihood under a consistency assumption, which enforces spectral properties linking the connection Laplacian to the underlying Laplacian.<n>We introduce the Structured Connection Graph Learning (SCGL) algorithm, a block-optimization procedure that jointly infers network topology, edge weights, and geometric structure.
  arXiv  Detail & Related papers  (2025-10-13T10:33:31Z)
• A Remedy for Over-Squashing in Graph Learning via Forman-Ricci Curvature based Graph-to-Hypergraph Structural Lifting [0.0]
  We propose a structural lifting strategy using Forman-Ricci curvature, which defines an edge-based network characteristic.<n>Curvature reveals local and global properties of a graph, such as a network's backbones.<n>Our approach provides a remedy to the problem of information distortion in message passing across long distances and graph bottlenecks.
  arXiv  Detail & Related papers  (2025-08-15T10:46:27Z)
• GraphProp: Training the Graph Foundation Models using Graph Properties [24.318377459225637]
  This work focuses on training graph foundation models (GFMs) that have strong generalization ability in graph-level tasks such as graph classification.<n>We discover that graph structures provide more consistent cross-domain information compared to node features and graph labels.<n>Our experiments demonstrate that GraphProp significantly outperforms the competitors in supervised learning and few-shot learning, especially in handling graphs without node attributes.
  arXiv  Detail & Related papers  (2025-08-06T16:12:42Z)
• GrannGAN: Graph annotation generative adversarial networks [72.66289932625742]
  We consider the problem of modelling high-dimensional distributions and generating new examples of data with complex relational feature structure coherent with a graph skeleton. The model we propose tackles the problem of generating the data features constrained by the specific graph structure of each data point by splitting the task into two phases. In the first it models the distribution of features associated with the nodes of the given graph, in the second it complements the edge features conditionally on the node features.
  arXiv  Detail & Related papers  (2022-12-01T11:49:07Z)
• Graph Spectral Embedding using the Geodesic Betweeness Centrality [76.27138343125985]
  We introduce the Graph Sylvester Embedding (GSE), an unsupervised graph representation of local similarity, connectivity, and global structure. GSE uses the solution of the Sylvester equation to capture both network structure and neighborhood proximity in a single representation.
  arXiv  Detail & Related papers  (2022-05-07T04:11:23Z)
• SHGNN: Structure-Aware Heterogeneous Graph Neural Network [77.78459918119536]
  This paper proposes a novel Structure-Aware Heterogeneous Graph Neural Network (SHGNN) to address the above limitations. We first utilize a feature propagation module to capture the local structure information of intermediate nodes in the meta-path. Next, we use a tree-attention aggregator to incorporate the graph structure information into the aggregation module on the meta-path. Finally, we leverage a meta-path aggregator to fuse the information aggregated from different meta-paths.
  arXiv  Detail & Related papers  (2021-12-12T14:18:18Z)
• Dist2Cycle: A Simplicial Neural Network for Homology Localization [66.15805004725809]
  Simplicial complexes can be viewed as high dimensional generalizations of graphs that explicitly encode multi-way ordered relations. We propose a graph convolutional model for learning functions parametrized by the $k$-homological features of simplicial complexes.
  arXiv  Detail & Related papers  (2021-10-28T14:59:41Z)
• Spectral Graph Convolutional Networks With Lifting-based Adaptive Graph Wavelets [81.63035727821145]
  Spectral graph convolutional networks (SGCNs) have been attracting increasing attention in graph representation learning. We propose a novel class of spectral graph convolutional networks that implement graph convolutions with adaptive graph wavelets.
  arXiv  Detail & Related papers  (2021-08-03T17:57:53Z)
• Ego-based Entropy Measures for Structural Representations on Graphs [35.55543331773255]
  VNEstruct is a simple approach, based on entropy measures of the neighborhood's topology, for generating low-dimensional structural representations. VNEstruct can achieve state-of-the-art performance on graph classification, without incorporating the graph structure information in the optimization.
  arXiv  Detail & Related papers  (2021-02-17T12:55:50Z)

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.