---
license: mit
library_name: pytorch
tags:
  - graph-foundation-model
  - graph-neural-network
  - node-classification
  - link-prediction
  - transfer-learning
  - relation-aware
pipeline_tag: graph-ml
---

# REEF: Relation-Aware Graph Foundation Model

> 🎉 **Accepted at NeurIPS 2026.**
>
> 📄 **Paper:** [Arxiv](https://arxiv.org/abs/2505.12027v2)  |  💻 **Code:** [GitHub](https://github.com/jianxiangyu/REEF/)


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

```bibtex
@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}
}
```