From a195f887b6c660001a641afc280292da1fab6ee5 Mon Sep 17 00:00:00 2001
From: sys1874 <578417645@qq.com>
Date: Fri, 25 Sep 2020 19:48:10 +0800
Subject: [PATCH] Update README.MD

---
 ogb_examples/nodeproppred/unimp/README.MD | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/ogb_examples/nodeproppred/unimp/README.MD b/ogb_examples/nodeproppred/unimp/README.MD
index d63f65e..34f61b1 100644
--- a/ogb_examples/nodeproppred/unimp/README.MD
+++ b/ogb_examples/nodeproppred/unimp/README.MD
@@ -2,6 +2,15 @@
 
 This experiment is based on stanford OGB (1.2.1) benchmark. The description of 《Masked Label Prediction: Unified Massage Passing Model for Semi-Supervised Classification》 is [avaiable here](https://arxiv.org/pdf/2009.03509.pdf). The steps are:
 
+### Note!
+We propose **UniMP_large**, where we extend our base model's width by increasing ```head_num```, and make it deeper by incorporating [APPNP](https://www.in.tum.de/daml/ppnp/) . Moreover, we firstly propose a new **Attention based APPNP** to further improve our model's performance.
+
+To_do list:
+- [x] UniMP_large in Arxiv
+- [ ] UniMP_large in Products
+- [ ] UniMP_large in Proteins
+- [ ] UniMP_xxlarge
+
 ### Install environment:
 ``` 
     git clone https://github.com/PaddlePaddle/PGL.git
@@ -13,6 +22,7 @@ This experiment is based on stanford OGB (1.2.1) benchmark. The description of 
 ### Arxiv dataset:
   1. ```python main_arxiv.py --place 0 --log_file arxiv_baseline.txt``` to get the baseline result of arxiv dataset.
   2. ```python main_arxiv.py --place 0 --use_label_e --log_file arxiv_unimp.txt``` to get the UniMP result of arxiv dataset.
+  3. ```python main_arxiv_large.py --place 0 --use_label_e --log_file arxiv_unimp_large.txt``` to get the UniMP_large result of arxiv dataset.
   
 ### Products dataset:
   1. ```python main_product.py --place 0 --log_file product_unimp.txt --use_label_e``` to get the UniMP result of Products dataset.
@@ -41,6 +51,7 @@ Arxiv_dataset(Full Batch):          Products_dataset(NeighborSampler):
 | ------------------ |--------------   | --------------- | -------------- |----------|
 | Arxiv_baseline     | 0.7225  ± 0.0015 | 0.7367  ± 0.0012 | 468,369  | Tesla V100 (32GB) |
 | Arxiv_UniMP        | 0.7311  ± 0.0021 | 0.7450  ± 0.0005 | 473,489 | Tesla V100 (32GB) |
+| Arxiv_UniMP_large        | 0.7379  ± 0.0014 | 0.7475  ± 0.0008 | 1,162,515 | Tesla V100 (32GB) |
 | Products_baseline  | 0.8023  ± 0.0026 | 0.9286  ± 0.0017 | 1,470,905  | Tesla V100 (32GB) |
 | Products_UniMP     | 0.8256  ± 0.0031 | 0.9308  ± 0.0017 | 1,475,605  | Tesla V100 (32GB) |
 | Proteins_baseline  | 0.8611  ± 0.0017 | 0.9128  ± 0.0007 | 1,879,664  | Tesla V100 (32GB) |
-- 
GitLab