Add pipeline tag and link to original Relational Transformer paper

#1
by nielsr HF Staff - opened
Files changed (1) hide show
  1. README.md +26 -15
README.md CHANGED
@@ -1,6 +1,12 @@
1
  ---
2
- license: mit
 
3
  library_name: pytorch
 
 
 
 
 
4
  tags:
5
  - relational-data
6
  - tabular
@@ -9,30 +15,34 @@ tags:
9
  - relational-transformer
10
  - relbench
11
  - synthetic-data
12
- datasets:
13
- - kvignesh1420/plurel
14
- metrics:
15
- - roc_auc
16
- - r_squared
17
  ---
18
 
19
  # Relational Transformer — PluRel Checkpoints
20
 
21
- Relational Transformer (RT) model checkpoints pretrained on synthetic relational databases generated by [PluRel](https://huggingface.co/datasets/kvignesh1420/plurel), as introduced in:
 
 
 
 
 
 
 
22
 
23
- > **PluRel: Synthetic Data unlocks Scaling Laws for Relational Foundation Models**
24
- > Kothapalli, Ranjan, Hudovernik, Dwivedi, Hoffart, Guestrin, Leskovec — arXiv:2602.04029 (2026)
25
 
26
- [![arXiv](https://img.shields.io/badge/arXiv-2602.04029-b31b1b?style=flat&logo=arxiv)](https://arxiv.org/abs/2602.04029)
27
- [![Project Page](https://img.shields.io/badge/Project-Page-blue?style=flat&logo=github)](https://snap-stanford.github.io/plurel/)
28
- [![GitHub](https://img.shields.io/badge/Code-GitHub-black?style=flat&logo=github)](https://github.com/snap-stanford/plurel)
 
 
29
  [![Dataset](https://img.shields.io/badge/Dataset-HuggingFace-yellow?style=flat&logo=huggingface)](https://huggingface.co/datasets/kvignesh1420/plurel)
30
 
31
  ---
32
 
33
  ## Model Architecture
34
 
35
- The Relational Transformer operates on multi-tabular relational databases, treating rows across linked tables as a sequence via BFS-ordered context sampling.
36
 
37
  | Hyperparameter | Value |
38
  |----------------|-------|
@@ -44,7 +54,7 @@ The Relational Transformer operates on multi-tabular relational databases, treat
44
  | Text encoder | `all-MiniLM-L12-v2` (d_text = 384) |
45
  | Max BFS width | 128 |
46
 
47
- The architecture and training loop build on the [Relational Transformer (ICLR 2026)](https://arxiv.org/abs/2510.06377) codebase.
48
 
49
  ---
50
 
@@ -53,4 +63,5 @@ The architecture and training loop build on the [Relational Transformer (ICLR 20
53
  ```bash
54
  huggingface-cli download kvignesh1420/relational-transformer-plurel \
55
  --repo-type model \
56
- --local-dir ~/scratch/rt_hf_ckpts
 
 
1
  ---
2
+ datasets:
3
+ - kvignesh1420/plurel
4
  library_name: pytorch
5
+ license: mit
6
+ pipeline_tag: other
7
+ metrics:
8
+ - roc_auc
9
+ - r_squared
10
  tags:
11
  - relational-data
12
  - tabular
 
15
  - relational-transformer
16
  - relbench
17
  - synthetic-data
 
 
 
 
 
18
  ---
19
 
20
  # Relational Transformer — PluRel Checkpoints
21
 
22
+ Relational Transformer (RT) model checkpoints pretrained on synthetic relational databases generated by [PluRel](https://huggingface.co/datasets/kvignesh1420/plurel).
23
+
24
+ Relational Transformer is a foundation model architecture for relational data that enables zero-shot transfer across heterogeneous schemas and tasks. It was introduced in:
25
+
26
+ > **Relational Transformer: Toward Zero-Shot Foundation Models for Relational Data**
27
+ > Rishabh Ranjan, Valter Hudovernik, Mark Znidar, Charilaos Kanatsoulis, Roshan Upendra, Mahmoud Mohammadi, Joe Meyer, Tom Palczewski, Carlos Guestrin, Jure Leskovec — [arXiv:2510.06377](https://arxiv.org/abs/2510.06377) (ICLR 2026)
28
+
29
+ The checkpoints provided in this repository were trained using the methodology described in:
30
 
31
+ > **PluRel: Synthetic Data unlocks Scaling Laws for Relational Foundation Models**
32
+ > Kothapalli, Ranjan, Hudovernik, Dwivedi, Hoffart, Guestrin, Leskovec — [arXiv:2602.04029](https://arxiv.org/abs/2602.04029) (2026)
33
 
34
+ [![arXiv (RT)](https://img.shields.io/badge/arXiv-2510.06377-b31b1b?style=flat&logo=arxiv)](https://arxiv.org/abs/2510.06377)
35
+ [![GitHub (RT)](https://img.shields.io/badge/Code-RT_GitHub-black?style=flat&logo=github)](https://github.com/snap-stanford/relational-transformer)
36
+ [![arXiv (PluRel)](https://img.shields.io/badge/arXiv-2602.04029-b31b1b?style=flat&logo=arxiv)](https://arxiv.org/abs/2602.04029)
37
+ [![Project Page (PluRel)](https://img.shields.io/badge/Project-Page-blue?style=flat&logo=github)](https://snap-stanford.github.io/plurel/)
38
+ [![GitHub (PluRel)](https://img.shields.io/badge/Code-PluRel_GitHub-black?style=flat&logo=github)](https://github.com/snap-stanford/plurel)
39
  [![Dataset](https://img.shields.io/badge/Dataset-HuggingFace-yellow?style=flat&logo=huggingface)](https://huggingface.co/datasets/kvignesh1420/plurel)
40
 
41
  ---
42
 
43
  ## Model Architecture
44
 
45
+ The Relational Transformer operates on multi-tabular relational databases, treating rows across linked tables as a sequence via BFS-ordered context sampling. It utilizes a Relational Attention mechanism over columns, rows, and primary-foreign key links.
46
 
47
  | Hyperparameter | Value |
48
  |----------------|-------|
 
54
  | Text encoder | `all-MiniLM-L12-v2` (d_text = 384) |
55
  | Max BFS width | 128 |
56
 
57
+ The architecture and training loop build on the [Relational Transformer](https://github.com/snap-stanford/relational-transformer) codebase.
58
 
59
  ---
60
 
 
63
  ```bash
64
  huggingface-cli download kvignesh1420/relational-transformer-plurel \
65
  --repo-type model \
66
+ --local-dir ~/scratch/rt_hf_ckpts
67
+ ```