mlsanityData to 14 Oct 2026

H2GFM: Towards unifying Homogeneity and Heterogeneity on Text-Attributed Graphs

arXiv 2506.08298 ↗First posted 10 Jun 2025cs.LG cs.SIcited by 0

Not on the map. Why?

Abstract (arXiv)

The growing interests and applications of graph learning in diverse domains have propelled the development of a unified model generalizing well across different graphs and tasks, known as the Graph Foundation Model (GFM). Existing research has leveraged text-attributed graphs (TAGs) to tackle the heterogeneity in node features among graphs. However, they primarily focus on homogeneous TAGs (HoTAGs), leaving heterogeneous TAGs (HeTAGs), where multiple types of nodes/edges reside, underexplored. To enhance the capabilities and applications of GFM, we introduce H2GFM, a novel framework designed to generalize across both HoTAGs and HeTAGs. Our model projects diverse meta-relations among graphs under a unified textual space, and employs a context encoding to capture spatial and higher-order semantic relationships. To achieve robust node representations, we propose a novel context-adaptive graph transformer (CGT), effectively capturing information from both context neighbors and their relationships. Furthermore, we employ a mixture of CGT experts to capture the heterogeneity in structural patterns among graph types. Comprehensive experiments on a wide range of HoTAGs and HeTAGs as well as learning scenarios demonstrate the effectiveness of our model.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 32 of its 45 references that are in the map. First posted on arXiv 10 Jun 2025.

Builds on

32 of 45 references.

References · 32

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  3. 2017Graph Attention Networkscited by 8,923
  4. 2018How Powerful are Graph Neural Networks?cited by 4,393
  5. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
  6. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  7. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,333
  8. 2020Graph Contrastive Learning with Augmentationscited by 1,208
  9. 2018Deep Graph Infomaxcited by 1,106
  10. 2019Heterogeneous Graph Attention Networkcited by 734
  11. 2020Heterogeneous Graph Transformercited by 582
  12. 2020Graph Neural Networks in Recommender Systems: A Surveycited by 494
20 more
  1. 2022GraphMAE: Self-Supervised Masked Graph Autoencoderscited by 448
  2. 2023One for All: Towards Training One Graph Model for All Classification Taskscited by 243
  3. 2024LLaGA: Large Language and Graph Assistantcited by 181
  4. 2021Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networkscited by 176
  5. 2021Self-supervised Heterogeneous Graph Neural Network with Co-contrastive Learningcited by 130
  6. 2020A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sourcescited by 126
  7. 2023Graph Foundation Models: Concepts, Opportunities and Challengescited by 103
  8. 2023PRODIGY: Enabling In-context Learning Over Graphscited by 98
  9. 2019Unsupervised Attributed Multiplex Network Embeddingcited by 95
  10. 2024GFT: Graph Foundation Model with Transferable Tree Vocabularycited by 85
  11. 2024UniGraph: Learning a Unified Cross-Domain Foundation Model for Text-Attributed Graphscited by 66
  12. 2023Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modelingcited by 64
  13. 2024LLMs as Zero-shot Graph Learners: Alignment of GNN Representations with LLM Token Embeddingscited by 61
  14. 2024AnyGraph: Graph Foundation Model in the Wildcited by 53
  15. 2024HiGPT: Heterogeneous Graph Language Modelcited by 45
  16. 2024Text-space Graph Foundation Models: Comprehensive Benchmarks and New Insightscited by 44
  17. 2024One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphscited by 12
  18. 2024Mixture of Link Predictors on Graphscited by 10
  19. 2023Link Prediction on Latent Heterogeneous Graphscited by 5
  20. 2024Multi-Scale Heterogeneous Text-Attributed Graph Datasets From Diverse Domainscited by 5

Built on by

Not cited yet.