Update: a new 50g ckpts, HF Hub release

Author: migalkin

README.md

@@ -5,6 +5,7 @@
 [![pytorch](https://img.shields.io/badge/PyTorch_2.1+-ee4c2c?logo=pytorch&logoColor=white)](https://pytorch.org/get-started/locally/)
 [![pyg](https://img.shields.io/badge/PyG_2.4+-3C2179?logo=pyg&logoColor=#3C2179)](https://pytorch-geometric.readthedocs.io/en/latest/install/installation.html)
 [![arxiv](http://img.shields.io/badge/arxiv-2310.04562-yellow.svg)](https://arxiv.org/abs/2310.04562)
+[![HuggingFace Hub](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Models-black)](https://huggingface.co/collections/mgalkin/ultra-65699bb28369400a5827669d)
 ![license](https://img.shields.io/badge/License-MIT-green.svg?labelColor=gray)
 
 </div>
@@ -47,6 +48,11 @@ Table of contents:
 * [Datasets](#datasets)
     * [Adding custom datasets](#adding-your-own-graph)
 
+## Updates
+
+* **Dec 4th, 2023**: Added a new ULTRA checkpoint `ultra_50g` pre-trained on 50 graphs. Averaged over 16 larger transductive graphs, it delivers 0.389 MRR / 0.549 Hits@10 compared to 0.329 MRR / 0.479 Hits@10 of the `ultra_3g` checkpoint. The inductive performance is still as good! Use this checkpoint for inference on larger graphs.
+* **Dec 4th, 2023**: Pre-trained ULTRA models (3g, 4g, 50g) are now also available on the [HuggingFace Hub](https://huggingface.co/collections/mgalkin/ultra-65699bb28369400a5827669d)! 
+
 ## Installation ##
 
 You may install the dependencies via either conda or pip.