Commit
•
7ed0073
1
Parent(s):
c3ecd81
Update README.md
Browse files
README.md
CHANGED
@@ -4,5 +4,67 @@ tags:
|
|
4 |
- graphs
|
5 |
---
|
6 |
|
|
|
|
|
7 |
The Graphormer is a graph classification model.
|
8 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
- graphs
|
5 |
---
|
6 |
|
7 |
+
# Model Card for pcqm4mv1_graphormer_base
|
8 |
+
|
9 |
The Graphormer is a graph classification model.
|
10 |
+
|
11 |
+
# Model Details
|
12 |
+
|
13 |
+
## Model Description
|
14 |
+
|
15 |
+
The Graphormer is a graph Transformer model, pretrained on PCQM4M-LSCv2.
|
16 |
+
|
17 |
+
|
18 |
+
- **Developed by:** Microsoft
|
19 |
+
- **Model type:** Graphormer
|
20 |
+
- **License:** MIT
|
21 |
+
|
22 |
+
## Model Sources
|
23 |
+
|
24 |
+
<!-- Provide the basic links for the model. -->
|
25 |
+
|
26 |
+
- **Repository:** [Github](https://github.com/microsoft/Graphormer)
|
27 |
+
- **Paper:** [Paper](https://arxiv.org/abs/2106.05234)
|
28 |
+
- **Documentation:** [Link](https://graphormer.readthedocs.io/en/latest/)
|
29 |
+
|
30 |
+
# Uses
|
31 |
+
|
32 |
+
## Direct Use
|
33 |
+
|
34 |
+
This model should be used for graph classification tasks or graph representation tasks; the most likely associated task is molecule modeling. It can either be used as such, or finetuned on downstream tasks.
|
35 |
+
|
36 |
+
# Bias, Risks, and Limitations
|
37 |
+
|
38 |
+
The Graphormer model is ressource intensive for large graphs, and might lead to OOM errors.
|
39 |
+
|
40 |
+
## How to Get Started with the Model
|
41 |
+
|
42 |
+
See the Graph Classification with Transformers tutorial.
|
43 |
+
|
44 |
+
# Citation [optional]
|
45 |
+
|
46 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
47 |
+
|
48 |
+
**BibTeX:**
|
49 |
+
```
|
50 |
+
@article{DBLP:journals/corr/abs-2106-05234,
|
51 |
+
author = {Chengxuan Ying and
|
52 |
+
Tianle Cai and
|
53 |
+
Shengjie Luo and
|
54 |
+
Shuxin Zheng and
|
55 |
+
Guolin Ke and
|
56 |
+
Di He and
|
57 |
+
Yanming Shen and
|
58 |
+
Tie{-}Yan Liu},
|
59 |
+
title = {Do Transformers Really Perform Bad for Graph Representation?},
|
60 |
+
journal = {CoRR},
|
61 |
+
volume = {abs/2106.05234},
|
62 |
+
year = {2021},
|
63 |
+
url = {https://arxiv.org/abs/2106.05234},
|
64 |
+
eprinttype = {arXiv},
|
65 |
+
eprint = {2106.05234},
|
66 |
+
timestamp = {Tue, 15 Jun 2021 16:35:15 +0200},
|
67 |
+
biburl = {https://dblp.org/rec/journals/corr/abs-2106-05234.bib},
|
68 |
+
bibsource = {dblp computer science bibliography, https://dblp.org}
|
69 |
+
}
|
70 |
+
```
|