REEF: Relation-Aware Graph Foundation Model

🎉 Accepted at NeurIPS 2026.

📄 Paper: Relation-Aware Graph Foundation Model  |  💻 Code: GitHub

REEF is a graph foundation model (GFM) that treats relations as the fundamental transferable unit of graphs. Each relation type (a citation link, a molecular bond, a knowledge-graph predicate, …) is described in natural language, encoded by a sentence encoder, and turned by three hypernetworks into:

1. a relation-specific aggregator for message passing,
2. a relation-specific classifier for downstream prediction, and
3. a dataset-specific projector + feature bias that adapts to different feature distributions.

A single pretrained model therefore transfers across datasets, domains, and tasks (node classification, link prediction) in zero-shot and few-shot settings.

Files in this repository

File	Size	Description
reef_pretrained.pth	~677 MB	Pretrained state_dict of the GFM model (PyTorch pickle).
edge_texts2id.json	~30 KB	Relation-text → id mapping (254 relations) used to look up relation tokens.

Training data

Pretrained on graphs spanning four domains:

• Knowledge graphs: FB15K237, WN18RR
• Citation networks: Citeseer, Pubmed
• Web pages (heterophilous): Texas, Wisconsin
• Co-purchase: Photo

Relation descriptions are encoded with Sentence-BERT (all-MiniLM-L6-v2). The relation vocabulary contains 254 relations (237 from FB15K237, 11 from WN18RR, and 6 domain-level descriptions), each with an LLM-generated textual description.

Citation

@article{yu2025relation,
  title={Relation-Aware Graph Foundation Model},
  author={Yu, Jianxiang and Zhu, Jiapeng and Qian, Hao and Liu, Ziqi and Zhang, Zhiqiang and Li, Xiang},
  journal={arXiv preprint arXiv:2505.12027},
  year={2025}
}