| Documentation | Blog | Paper | Slide |

---

Latest News 🔥

• [2026.07] Our paper InRTL was accepted by KDD 2026, leveraging the rLLM algorithm library and SJTUTables benchmark (GitHub). See the paper and code.
• [2026.01] Released TLSQL, a SQL-like API for table learning. See the paper, code, and demo.
• [2025.10] Our students won 1st Prize in the China Open Source Security Incentive Program.
• [2025.08] At the CCF–Huawei Populus Grove Fund midterm report, we showed how to use rLLM in a "SQL-like" way with MySQL. Watch the video on Huawei’s official account: 📺 Bilibili.
• [2025.04] Released the course videos "Special Topic on Table Learning (Spring 2025, SJTU)". Check out the course page or visit our YouTube channel.
• [2025.01] We’ve updated to rLLM v0.1.1 for improved uniformity between Transform and Convolution operations. See our blog.
• [2024.12] rLLM was featured in the famous technical magzine MIT Technology Review. Read the report here (Chinese) or here (English).
• [2024.11] This work has been approved by Snowflake (AI Data Cloud leader, NYSE: $57.46B) as a nice tool for RTL-type tasks. See paper: arXiv:2411.11829.
• [2024.10] We have recently added the state-of-the-art GNN method OGC [TNNLS 2024], the TNN method ExcelFormer [KDD 2024] and Trompt [ICML 2023].
• [2024.08] rLLM is supported by the CCF-Huawei Populus Grove Fund (CCF-华为胡杨林基金数据库专项). This project focuses on Tabular Data Governance for AI Tasks. Watch a short introduction video on Huawei's official account: 📺 Bilibili.
• [2024.07] We have released rLLM (v0.1), and the detailed documentation is now available: rLLM Documentation.

---

About

rLLM (relationLLM) is an easy-to-use Pytorch library for Relational Table Learning (RTL) with LLMs, by performing two key functions:

1. Breaks down state-of-the-art GNNs, LLMs, and TNNs as standardized modules.
2. Facilitates novel model building in a "combine, align, and co-train" way.

How to Try

Let's run an RTL-type method BRIDGE as an example:

# cd ./examples/bridge
# set parameters if necessary

python bridge.py

Highlight Features

• LLM-friendly: Modular interface designed for LLM-oriented applications, integrating smoothly with LangChain and Hugging Face transformers.
• One-Fit-All Potential: Processes various graphs (like Social/Citation/E-commerce Networks) by treating them as multiple tables linked by foreigner keys.
• Novel Datasets: Introduces three new relational table datasets useful for RTL model design. Includes the standard classification task, with examples.
• Community Support: Maintained by students and teachers from Shanghai Jiao Tong University and Tsinghua University. Supports the SJTU undergraduate course "Content Understanding (NIS4301)" and the graduate course "Social Network Analysis (NIS8023)".

Implemented Methods

rLLM includes over 15 state-of-the-art GNN and TNN models, ideal for both standalone use and building RTL-type methods. Highlighted models include:

• InRTL: Effective Intra-Inter Interaction Learning for Relational Tables [KDD 2026] [Example]

• OGC: From Cluster Assumption to Graph Convolution: Graph-based Semi-Supervised Learning Revisited [TNNLS 2024] [Example]

• ExcelFormer: ExcelFormer: A Neural Network Surpassing GBDTs on Tabular Data [KDD 2024] [Example]

• TAPE: Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning [ICLR 2024] [Example]

• Trompt: Towards a Better Deep Neural Network for Tabular Data [ICML 2023] [Example]

• ...

Contributing

Contribution is always welcomed. All contributions must be made through pull requests and are subject to review by the committers. For more details, please refer to our [contribution guide].

Todo List

• Code structure optimization
• Support for more TNNs
• Large-scale RTL training
• GPU/TPU optimization
• LLM prompt optimization

Sponsor

For more cooperation, feel free to contact Zheng Wang.

Citation

@article{rllm2024,
      title={rLLM: Relational Table Learning with LLMs}, 
      author={Weichen Li and Xiaotong Huang and Jianwu Zheng and Zheng Wang and Chaokun Wang and Li Pan and Jianhua Li},
      year={2024},
      eprint={2407.20157},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2407.20157}, 
}
@inproceedings{li2026effective,
  title={Effective Intra-Inter Interaction Learning for Relational Tables},
  author={Li, Weichen and Zhong, Ken and Wang, Zheng and Pan, Li and Li, Jianhua},
  booktitle={Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V. 2},
  pages={2742--2753},
  year={2026}
}