GraphProp: Training the Graph Foundation Models using Graph Properties

• URL: http://arxiv.org/abs/2508.04594v1
• Date: Wed, 06 Aug 2025 16:12:42 GMT
• Title: GraphProp: Training the Graph Foundation Models using Graph Properties
• Abstract summary: 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.
• Score: 24.318377459225637
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This work focuses on training graph foundation models (GFMs) that have strong generalization ability in graph-level tasks such as graph classification. Effective GFM training requires capturing information consistent across different domains. We discover that graph structures provide more consistent cross-domain information compared to node features and graph labels. However, traditional GFMs primarily focus on transferring node features from various domains into a unified representation space but often lack structural cross-domain generalization. To address this, we introduce GraphProp, which emphasizes structural generalization. The training process of GraphProp consists of two main phases. First, we train a structural GFM by predicting graph invariants. Since graph invariants are properties of graphs that depend only on the abstract structure, not on particular labellings or drawings of the graph, this structural GFM has a strong ability to capture the abstract structural information and provide discriminative graph representations comparable across diverse domains. In the second phase, we use the representations given by the structural GFM as positional encodings to train a comprehensive GFM. This phase utilizes domain-specific node attributes and graph labels to further improve cross-domain node feature generalization. Our experiments demonstrate that GraphProp significantly outperforms the competitors in supervised learning and few-shot learning, especially in handling graphs without node attributes.

Related papers

• Surprisingly Simple and Effective Multi-Domain Graph Foundation Model through Graph-to-Table Alignment [27.039467001269614]
  Graph Foundation Models (GFMs) have emerged as a promising paradigm for learning transferable representations across diverse graph domains.<n>We propose GTAlign, a surprisingly simple yet effective Graph-to-Table alignment framework for text-free Graph Foundation Model.<n>Experiments on five benchmark datasets demonstrate that GTAlign significantly outperforms state-of-the-art baselines on both node and graph classification.
  arXiv  Detail & Related papers  (2026-07-13T10:35:56Z)
• Structure-Centric Graph Foundation Model via Geometric Bases [16.191907209297362]
  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.
  arXiv  Detail & Related papers  (2026-05-09T04:56:21Z)
• Training A Foundation Model to Represent Graphs as Vectors [24.592499205332413]
  This paper aims to train a graph foundation model that is able to represent any graph as a vector preserving semantic information.<n>We provide a theoretical generalization bound to support the effectiveness of the proposed model.<n>The experimental results of few-shot graph classification and graph clustering show that our model outperforms strong baselines.
  arXiv  Detail & Related papers  (2026-02-04T06:06:28Z)
• From Features to Structure: Task-Aware Graph Construction for Relational and Tabular Learning with GNNs [6.0757501646966965]
  We introduce auGraph, a unified framework for task-aware graph augmentation.<n> auGraph enhances base graph structures by selectively promoting attributes into nodes.<n>It preserves the original data schema while injecting task-relevant structural signal.
  arXiv  Detail & Related papers  (2025-06-02T20:42:53Z)
• It Takes a Graph to Know a Graph: Rewiring for Homophily with a Reference Graph [19.222317334613162]
  Graph Neural Networks (GNNs) excel at analyzing graph-structured data but struggle on heterophilic graphs, where connected nodes often belong to different classes.<n>We provide theoretical foundations linking edge homophily, GNN embedding smoothness, and node classification performance.<n>We introduce a rewiring framework that increases graph homophily using a reference graph, with theoretical guarantees on the homophily of the rewired graph.
  arXiv  Detail & Related papers  (2025-05-18T13:28:56Z)
• GaGSL: Global-augmented Graph Structure Learning via Graph Information Bottleneck [5.943641527857957]
  We propose a novel method named textitGlobal-augmented Graph Structure Learning (GaGSL) The key idea behind GaGSL is to learn a compact and informative graph structure for node classification tasks. Comprehensive evaluations across a range of datasets reveal the outstanding performance and robustness of GaGSL compared with the state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-11-07T01:23:48Z)
• InstructG2I: Synthesizing Images from Multimodal Attributed Graphs [50.852150521561676]
  We propose a graph context-conditioned diffusion model called InstructG2I. InstructG2I first exploits the graph structure and multimodal information to conduct informative neighbor sampling. A Graph-QFormer encoder adaptively encodes the graph nodes into an auxiliary set of graph prompts to guide the denoising process.
  arXiv  Detail & Related papers  (2024-10-09T17:56:15Z)
• Boosting Graph Foundation Model from Structural Perspective [6.387816922598151]
  We boost graph foundation model from structural perspective and propose BooG. BooG constructs virtual super nodes to unify structural characteristics of graph data from different domains. We also propose a novel pre-training objective based on contrastive learning, which learns more expressive representations for graph data.
  arXiv  Detail & Related papers  (2024-07-29T12:22:16Z)
• GraphAlign: Pretraining One Graph Neural Network on Multiple Graphs via Feature Alignment [30.56443056293688]
  Graph self-supervised learning (SSL) holds considerable promise for mining and learning with graph-structured data. In this work, we aim to pretrain one graph neural network (GNN) on a varied collection of graphs endowed with rich node features. We present a general GraphAlign method that can be seamlessly integrated into the existing graph SSL framework.
  arXiv  Detail & Related papers  (2024-06-05T05:22:32Z)
• OpenGraph: Towards Open Graph Foundation Models [20.401374302429627]
  Graph Neural Networks (GNNs) have emerged as promising techniques for encoding structural information. Key challenge remains: the difficulty of generalizing to unseen graph data with different properties. We propose a novel graph foundation model, called OpenGraph, to address this challenge.
  arXiv  Detail & Related papers  (2024-03-02T08:05:03Z)
• Position: Graph Foundation Models are Already Here [53.737868336014735]
  Graph Foundation Models (GFMs) are emerging as a significant research topic in the graph domain. We propose a novel perspective for the GFM development by advocating for a graph vocabulary'' This perspective can potentially advance the future GFM design in line with the neural scaling laws.
  arXiv  Detail & Related papers  (2024-02-03T17:24:36Z)
• Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modeling [60.0185734837814]
  Graph neural networks (GNNs) have found extensive applications in learning from graph data. To bolster the generalization capacity of GNNs, it has become customary to augment training graph structures with techniques like graph augmentations. This study introduces the concept of Mixture-of-Experts (MoE) to GNNs, with the aim of augmenting their capacity to adapt to a diverse range of training graph structures.
  arXiv  Detail & Related papers  (2023-04-06T01:09:36Z)
• Spectral Augmentations for Graph Contrastive Learning [50.149996923976836]
  Contrastive learning has emerged as a premier method for learning representations with or without supervision. Recent studies have shown its utility in graph representation learning for pre-training. We propose a set of well-motivated graph transformation operations to provide a bank of candidates when constructing augmentations for a graph contrastive objective.
  arXiv  Detail & Related papers  (2023-02-06T16:26:29Z)
• Semi-Supervised Hierarchical Graph Classification [54.25165160435073]
  We study the node classification problem in the hierarchical graph where a 'node' is a graph instance. We propose the Hierarchical Graph Mutual Information (HGMI) and present a way to compute HGMI with theoretical guarantee. We demonstrate the effectiveness of this hierarchical graph modeling and the proposed SEAL-CI method on text and social network data.
  arXiv  Detail & Related papers  (2022-06-11T04:05:29Z)
• 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)

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.