Graph_algorithm/OpenANE
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

readme update (draft 2)

Browse Source
This commit is contained in:
Chengbin Hou 2018-11-29 20:56:42 +00:00
parent 6eefa603cb
commit c14f6854d3
1 changed files with 65 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

69
README.md
View File

@ -23,13 +23,20 @@ AttrPure,
AttrComb, AttrComb,
## Requirements (todo... Zeyu; double check) ## Requirements (todo... Zeyu; double check)
```bash
pip install -r requirements.txt pip install -r requirements.txt
```
Python 3.6 or above is required due to the [new print(f' ') feature](https://docs.python.org/3.6/reference/lexical_analysis.html#f-strings)
## Usages ## Usages
#### To obtain your node embeddings and evaluate them by classification downstream tasks #### To obtain your node embeddings and evaluate them by classification downstream tasks
```bash
python src/main.py --method abrw --emb-file cora_abrw_emb --save-emb python src/main.py --method abrw --emb-file cora_abrw_emb --save-emb
```
#### To have an intuitive feeling of node embeddings (todo... Zeyu if possible; need tf installed) #### To have an intuitive feeling of node embeddings (todo... Zeyu if possible; need tf installed)
```bash
python src/viz.py --emb-file cora_abrw_emb --label-file data/cora_label python src/viz.py --emb-file cora_abrw_emb --label-file data/cora_label
```
## Parameters ## Parameters
#### the meaning of each parameter #### the meaning of each parameter
@ -38,13 +45,67 @@ please see main.py
ABRW ABRW
SAGE-GCN SAGE-GCN
## Testing (todo... Zeyu) ## Testing
Currently, we use the default parameter....
.... summary of parameters .... ### Parameter Setting
.... table --- results .... Currently, we use the default parameter
| AANE_lamb | AANE_maxiter | AANE_rho | ABRW_alpha | ABRW_topk | ASNE_lamb | AttrComb_mode | GraRep_kstep | LINE_negative_ratio | LINE_order | Node2Vec_p | Node2Vec_q | TADW_lamb | TADW_maxiter | batch_size | dim | dropout | epochs | label_reserved | learning_rate | link_remove | number_walks | walk_length | weight_decay | window_size | workers |
|-----------|--------------|----------|------------|-----------|-----------|---------------|--------------|---------------------|------------|------------|------------|-----------|--------------|------------|-----|---------|--------|----------------|---------------|-------------|--------------|-------------|--------------|-------------|---------|
| 0.05 | 10 | 5 | 0.8 | 30 | 1 | concat | 4 | 5 | 3 | 0.5 | 0.5 | 0.2 | 10 | 128 | 128 | 0.5 | 100 | 0.7 | 0.001 | 0.1 | 10 | 80 | 0.0001 | 10 | 24 |
### Testing Result
**citeseer**:
| method | AUC | Micro-F1 | Macro-F1 | Time |
|----------|--------|----------|----------|----------|
| aane | 0.8889 | 0.7067 | 0.6295 | 36.99 |
| abrw | 0.9342 | 0.7287 | 0.6705 | 64.32 |
| asne | 0.8293 | 0.5275 | 0.4736 | 70.89 |
| attrcomb | 0.8756 | 0.7077 | 0.6592 | 99.19 |
| attrpure | 0.8684 | 0.6922 | 0.6525 | 0.99 |
| deepwalk | 0.7203 | 0.5681 | 0.5205 | 93.14 |
| grarep | 0.8501 | 0.5200 | 0.4656 | 16.48 |
| line | 0.6340 | 0.3959 | 0.3503 | 242.59 |
| node2vec | 0.6588 | 0.5931 | 0.5493 | 27.60 |
| sagegcn | 0.8953 | 0.6016 | 0.5247 | 444.50 |
| sagemean | 0.8772 | 0.6391 | 0.5606 | 371.74 |
| tadw | 0.8984 | 0.7337 | 0.6866 | 14.39 |
**cora:**
| method | AUC | Micro-F1 | Macro-F1 | Time |
|----------|--------|----------|----------|----------|
| aane | 0.8158 | 0.7263 | 0.6904 | 26.48 |
| abrw | 0.9290 | 0.8721 | 0.8603 | 48.94 |
| asne | 0.7842 | 0.6076 | 0.5649 | 69.67 |
| attrcomb | 0.9111 | 0.8444 | 0.8284 | 60.32 |
| attrpure | 0.7857 | 0.7349 | 0.7039 | 0.49 |
| deepwalk | 0.8499 | 0.8100 | 0.8021 | 75.15 |
| grarep | 0.8936 | 0.7669 | 0.7607 | 10.31 |
| line | 0.6945 | 0.5873 | 0.5645 | 259.02 |
| node2vec | 0.7938 | 0.7977 | 0.7858 | 29.42 |
| sagegcn | 0.8929 | 0.7780 | 0.7622 | 207.49 |
| sagemean | 0.8882 | 0.8057 | 0.7902 | 183.65 |
| tadw | 0.9005 | 0.8383 | 0.8255 | 10.73 |
**mit:**
| method | AUC | Micro-F1 | Macro-F1 | Time |
|----------|--------|----------|----------|----------|
| aane | 0.6586 | 0.3742 | 0.0730 | 83.49 |
| abrw | 0.9068 | 0.7981 | 0.2286 | 113.41 |
| asne | 0.6596 | 0.3041 | 0.0681 | 901.18 |
| attrcomb | 0.8548 | 0.8016 | 0.2223 | 125.82 |
| attrpure | 0.6464 | 0.3497 | 0.0707 | 1.19 |
| deepwalk | 0.9190 | 0.7997 | 0.2295 | 173.70 |
| grarep | 0.8983 | 0.7695 | 0.1901 | 51.55 |
| line | 0.7836 | 0.7415 | 0.1857 | 6335.43 |
| node2vec | 0.9088 | 0.8085 | 0.2356 | 465.54 |
| sagegcn | 0.8005 | 0.6057 | 0.1451 | 12462.35 |
| sagemean | 0.7525 | 0.5796 | 0.1279 | 10534.44 |
## Datasets (todo...Chengbin) ## Datasets (todo...Chengbin)
We provide Cora for ... and other datasets e.g. Facebook_MIT, refer to [NetEmb-Datasets](https://github.com/houchengbin/NetEmb-datasets) We provide Cora for ... and other datasets e.g. Facebook_MIT, refer to [NetEmb-Datasets](https://github.com/houchengbin/NetEmb-datasets)